To see the other types of publications on this topic, follow the link: Task oriented dialogue system.
Dissertations / Theses on the topic 'Task oriented dialogue system'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 38 dissertations / theses for your research on the topic 'Task oriented dialogue system.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
ISOMURA, Naoki, Fujio TORIUMI, and Kenichiro ISHII. "EVALUATION METHOD OF NON-TASK-ORIENTED DIALOGUE SYSTEM BY HMM." INTELLIGENT MEDIA INTEGRATION NAGOYA UNIVERSITY / COE, 2006. http://hdl.handle.net/2237/10479.
Full text
2
Yang, Fan. "Directing the flow of conversation in task-oriented dialogue." Full text open access at:, 2008. http://content.ohsu.edu/u?/etd,625.
Full text
3
Balaraman, Vevake. "Leveraging Domain Information for Data Driven Task-Oriented Dialogue Systems." Doctoral thesis, Università degli studi di Trento, 2022. http://hdl.handle.net/11572/339652.
Full textAbstract:
Task-oriented dialogue systems are designed to interact and assist users to achieve a certain goal. A typical approach to model such systems is a component-based approach that involves multiple components, each performing a sub-task of the dialogue system. These components are generally modelled based on a given domain with domain-specific features making them expensive to port to new domains and requiring large in-domain data. In this thesis we investigate the role of domain information in data-driven task-oriented systems. We note that domain information is widely unused in current neural models, and present several approaches that incorporate and take advantage of domain knowledge in different components of a dialogue system. More specifically, this thesis: i) presents a neural model for the entity recognition task focused on low-resource domains integrating large gazetteers as domain information; ii) presents an approach for single domain dialogue state trackers that incorporates domain information; iii) presents a multi-domain dialogue state tracker, which is able to read directly from domain schema and is able to make predictions even for unseen domains; iv) provides a survey on the recent neural approaches to dialogue state tracker by grouping neural models based on their approach; and v) proposes to incorporate domain knowledge for implementing a proactive strategy of a dialogue policy component. Both results and analysis of the experiments show the effectiveness of incorporating domain information as part of network modelling. Particularly, we address current limitations of neural models for task-oriented systems, such as requiring large training data, high latency response time, and flexibility with respect to domains.
4
Linné, Christoffer, and Pontus Olausson. "Crowdsourcing av data för Hybrid Code Networks." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-281968.
Full textAbstract:
Task-oriented dialogue systems are a popular way for organisations to generate extra value both internally and for customers. Modern approaches for these dialogue systems that use neural networks to enable training directly on written dialogues are very data hungry, which complicates their implementation. Crowdsourcing is an attractive solution for generating this type of training data, but the method also comes with several difficulties. We introduce a new method for generating training data based on parallel crowdsourcing of dialogues, as well as crowdsourced quality review. We use this method to collect a small dataset that takes place within the domain bus driver-traveler. We believe that this method offers an efficient way to collect new, high-quality datasets. Hybrid Code Networks is a model for dialogue systems that combines a neural network with domain-specific knowledge, and thus requires a significantly smaller amount of training data than other similar dialogue systems to achieve comparable performance. By combining Hybrid Code Networks with our new method for generating training data, we believe that the threshold for implementing task-oriented dialogue systems on domains with insufficient training data can be lowered. We implement Hybrid Code Networks and train the implementation on the collected dataset and achieve good results.Uppgiftsorienterade dialogsystem är ett populärt sätt för företag att generera extra värde både internt och för kunder. Moderna modeller för dessa dialogsystem som använder neurala nätverk för att möjliggöra träning direkt på skriftliga dialoger är väldigt datahungriga, vilket försvårar implementationen av dessa. Crowdsourcing är en attraktiv lösning för att generera denna typ av träningsdata, men metoden kommer även med flera svårigheter. Vi introducerar en ny metod för generering av träningsdata som bygger på parallell crowdsourcing av dialoger, samt crowdsourcad kvalitetsgranskning. Vi använder denna metod för att samla in ett litet dataset som utspelar sig inom domänen busschaufför-resenär. Vi menar att denna metod erbjuder ett effektivt sätt att samla in nya, högkvalitativa dataset. Hybrid Code Networks är en modell för dialogsystem som kombinerar ett neuralt nätverk med domänspecifik kunskap, och som på så sätt kräver en betydligt mindre mängd träningsdata än andra liknande dialogsystem för att uppnå jämförbar prestanda. Genom att kombinera Hybrid Code Networks med vår nya metod för generering av träningsdata menar vi att man kan sänka tröskeln för att implementera uppgiftsorienterade dialogsystem på domäner med otillräcklig träningsdata. Vi implementerar Hybrid Code Networks och tränar implementationen på det insamlade datasetet, och uppnår goda resultat.
5
Veron, Mathilde. "Systèmes de dialogue apprenant tout au long de leur vie : de l'élaboration à l'évaluation." Electronic Thesis or Diss., université Paris-Saclay, 2022. http://www.theses.fr/2022UPASG089.
Full textAbstract:
Les systèmes de dialogue orientés tâche, plus communément appelés chatbots, ont pour but de réaliser des tâches et de fournir des informations à la demande d’un utilisateur dans le cadre d’une conversation et d’un domaine précis (e.g. réservation d’un billet de train). Ces systèmes ont été largement adoptés par de nombreuses entreprises. Cependant, ils souffrent en pratique de certaines limitations : (1) ils sont dépendants des données d’entraînement nécessaires afin d’obtenir un système performant, (2) ils manquent de flexibilité et sont peu performants dès que le cas de figure rencontré en pratique s’éloigne des données vues pendant le développement, et (3) il est difficile de les adapter au cours du temps aux nouveaux éléments qui apparaissent étant donné l’évolution inévitable du monde et des exigences des concepteurs et des utilisateurs. Ainsi, nous appliquons le Lifelong Learning (LL) aux systèmes de dialogue orientés tâche. Nous définissons le LL comme la capacité d’un système à être appliqué à et à apprendre plusieurs tâches au cours du temps, en production, en autonomie, en continu et de manière interactive. Trois étapes doivent alors être réalisées en autonomie par le système : (1) Détecter la présence d’un nouvel élément, (2) extraire et identifier le nouvel élément et (3) adapter les composants du système associés à cet élément. Dans le cadre de cette thèse et étant donné la complexité du sujet, nous nous concentrons sur trois sous-problèmes liés aux systèmes de dialogue apprenant tout au long de leur vie. Dans un 1er temps, nous proposons une 1ère méthodologie pour l’évaluation continue et au cours du temps de l’apprentissage sur le terrain des systèmes de dialogue. Ce type d’apprentissage est proche du LL mais met de côté l’aspect multi-tâches. Nous décrivons aussi un système de dialogue orienté tâche capable d’améliorer sur le terrain sa détection des slots via l’annotation autonome de données collectées au cours de ses interactions. Nous évaluons ce système à travers deux méthodes d’adaptation grâce à notre méthodologie et montrons l’intérêt d’une évaluation continue et au cours du temps. Dans un 2nd temps, nous nous concentrons sur l’étude novatrice du transfert inter-langue dans le cadre de l’apprentissage continu d’une séquence de langues. En effet, le transfert et l’apprentissage continu sont deux aspects importants du LL. Nous réalisons cette étude sur la tâche de détection des slots à l’aide de BERT multilingue. Nous observons des capacités de transfert en avant substantielles malgré la présence d’oubli et présentons les capacités d’un modèle entraîné de manière continue. Dans un 3ème temps, nous nous intéressons à l’étude du transfert inter-domaine dans le cadre de l’apprentissage zero-shot. Nous réalisons cette étude sur la tâche de suivi de l’état du dialogue, qui nécessite de considérer l’ensemble du dialogue et plus seulement le tour courant. Nous étudions d’abord les capacités de généralisation et de transfert d’un modèle existant sur de nouvelles valeurs de slots. Ensuite, nous proposons des variantes du modèle et une méthode capable d’améliorer les performances zero-shot du modèle sur des nouveaux types de slots appartenant à un nouveau domaineTask-oriented dialogue systems, more commonly known as chatbots, are intended to perform tasks and provide the information required by a user in a conversation in a specific domain (e.g., train booking). These systems have been widely adopted by many companies. However, they suffer in practice from some limitations: (1) they are dependent on the training data needed to obtain a performing system, (2) they lack flexibility and perform poorly as soon as the case encountered in practice moves away from the data seen during development, and (3) it is difficult to adapt them over time to new elements that appear given the inevitable evolution of the world, of the requirements of the designers and users. Thus, we apply Lifelong Learning (LL) to task-oriented dialogue systems. We define LL as the ability of a system to be applied to and learn multiple tasks over time, in production, autonomously, continuously, and interactively. Three steps must be performed in autonomy by the system: (1) Detect the presence of a new element, (2) extract and identify the new element, and (3) adapt the system components associated with this element. As part of this thesis and given the complexity of LL, we focus our work on three subproblems associated with LL dialogue systems. As a first step, we propose a first methodology for the continuous and time-dependent evaluation of on-the-job learning dialogue systems. This type of learning is close to LL but puts aside the multitask aspect. We also describe a task-oriented dialogue system capable of improving its slot detection on-the-job via the autonomous annotation of data collected during its interactions. We evaluate this system through two adaptation methods using our methodology and show interest in a continuous evaluation over time. As a second step, we focus on the innovative study of interlingual transfer when applying continual learning to a language sequence. Indeed, transfer and continual learning are two main aspects of LL. We perform this study on the slot-filling task using multilingual BERT. We observe substantial forward transfer capabilities despite the presence of forgetting and demonstrate the capabilities of a model trained in a continual manner. As a third step, we study inter-domain transfer in the context of zero-shot learning. We carry out this study on a task that requires considering the whole dialogue and not only the current turn, which corresponds to the dialogue state tracking task. We first study the generalization and transfer capabilities of an existing model on new slot values. Then, we propose some model variants and a method able to improve the zero-shot performance of the model on new types of slots belonging to a new domain
6
Bouguelia, Sara. "Modèles de dialogue et reconnaissance d'intentions composites dans les conversations Utilisateur-Chatbot orientées tâches." Electronic Thesis or Diss., Lyon 1, 2023. http://www.theses.fr/2023LYO10106.
Full textAbstract:
Les Systèmes de Dialogue (ou simplement chatbots) sont très demandés de nos jours. Ils permettent de comprendre les besoins des utilisateurs (ou intentions des utilisateurs), exprimés en langage naturel, et de répondre à ces intentions en invoquant les APIs (Interfaces de Programmation d’Application) appropriées. Les chatbots sont connus pour leur interface facile à utiliser et ils ne nécessitent que l'une des capacités les plus innées des humains qui est l'utilisation du langage naturel. L'amélioration continue de l'Intelligence Artificielle (IA), du Traitement du Langage Naturel (NLP) et du nombre incalculable de dispositifs permettent d'effectuer des tâches réelles (par exemple, faire une réservation) en utilisant des interactions basées sur le langage naturel entre les utilisateurs et un grand nombre de services.Néanmoins, le développement de chatbots est encore à un stade préliminaire, avec plusieurs défis théoriques et techniques non résolus découlant de (i) la variations d'énoncés dans les interactions humain-chatbot en libre échange et (ii) du grand nombre de services logiciels potentiellement inconnus au moment du développement. Les conversations en langage naturel des personnes peuvent être riches, potentiellement ambiguës et exprimer des intentions complexes et dépendantes du contexte. Les techniques traditionnelles de modélisation et d'orchestration de processus et de composition de services sont limitées pour soutenir de telles conversations car elles supposent généralement une attente a priori de quelles informations et applications seront accédées et comment les utilisateurs exploreront ces sources et services. Limiter les conversations à un modèle de processus signifie que nous ne pouvons soutenir qu'une petite fraction de conversations possibles. Bien que les avancées existantes dans les techniques de NLP et d'apprentissage automatique (ML) automatisent diverses tâches telles que la reconnaissance d'intention, la synthèse d'appels API pour prendre en charge une large gamme d'intentions d'utilisateurs potentiellement complexes est encore largement un processus manuel et coûteux.Ce projet de thèse vise à faire avancer la compréhension fondamentale de l'ingénierie des services cognitifs. Dans cette thèse, nous contribuons à des abstractions et des techniques novatrices axées sur la synthèse d'appels API pour soutenir une large gamme d'intentions d'utilisateurs potentiellement complexes. Nous proposons des techniques réutilisables et extensibles pour reconnaître et réaliser des intentions complexes lors des interactions entre humains, chatbots et services. Ces abstractions et techniques visent à débloquer l'intégration transparente et évolutive de conversations basées sur le langage naturel avec des services activés par logicielDialogue Systems (or simply chatbots) are in very high demand these days. They enable the understanding of user needs (or user intents), expressed in natural language, and on fulfilling such intents by invoking the appropriate back-end APIs (Application Programming Interfaces). Chatbots are famed for their easy-to-use interface and gentle learning curve (it only requires one of humans' most innate ability, the use of natural language). The continuous improvement in Artificial Intelligence (AI), Natural Language Processing (NLP), and the countless number of devices allow performing real-world tasks (e.g., making a reservation) by using natural language-based interactions between users and a large number of software enabled services.Nonetheless, chatbot development is still in its preliminary stage, and there are several theoretical and technical challenges that need to be addressed. One of the challenges stems from the wide range of utterance variations in open-end human-chatbot interactions. Additionally, there is a vast space of software services that may be unknown at development time. Natural human conversations can be rich, potentially ambiguous, and express complex and context-dependent intents. Traditional business process and service composition modeling and orchestration techniques are limited to support such conversations because they usually assume a priori expectation of what information and applications will be accessed and how users will explore these sources and services. Limiting conversations to a process model means that we can only support a small fraction of possible conversations. While existing advances in NLP and Machine Learning (ML) techniques automate various tasks such as intent recognition, the synthesis of API calls to support a broad range of potentially complex user intents is still largely a manual, ad-hoc and costly process.This thesis project aims at advancing the fundamental understanding of cognitive services engineering. In this thesis we contribute novel abstractions and techniques focusing on the synthesis of API calls to support a broad range of potentially complex user intents. We propose reusable and extensible techniques to recognize and realize complex intents during humans-chatbots-services interactions. These abstractions and techniques seek to unlock the seamless and scalable integration of natural language-based conversations with software-enabled services
7
Schaub, Léon-Paul. "Dimensions mémorielles de l'interaction écrite humain-machine ˸ une approche cognitive par les modèles mnémoniques pour la détection et la correction des incohérences du système dans les dialogues orientés-tâche." Electronic Thesis or Diss., université Paris-Saclay, 2022. http://www.theses.fr/2022UPASG023.
Full textAbstract:
Dans ce travail, nous nous intéressons à la place des systèmes de dialogue orientés-tâche à la fois dans le traitement automatique des langues, et dans l’interaction humain-machine. Nous nous concentrons plus particulièrement sur la différence de traitement de l’information et de l’utilisation de la mémoire, d’un tour de parole à l’autre, par l’humain et la machine, pendant une conversation écrite de type clavardage. Après avoir étudié les mécanismes de rétention et de rappel mémoriels chez l’humain durant un dialogue, en particulier dans l'accomplissement d'une tâche, nous émettons l’hypothèse qu’un des éléments susceptible d'expliquer que les performances des machines demeurent en deçà de celles des humains, est la capacité à posséder non seulement une image de l’utilisateur, mais également une image de soi, explicitement convoquée pendant les inférences liées à la poursuite du dialogue. Cela se traduit pour le système par les trois axes suivants. Tout d’abord, par l’anticipation, à un tour de parole donné, du tour suivant de l’utilisateur. Ensuite, par la détection d’une incohérence dans son propre énoncé, facilitée, comme nous le démontrons, par l’anticipation du tour suivant de l’utilisateur en tant qu’indice supplémentaire. Enfin, par la prévision du nombre de tours de paroles restants dans le dialogue afin d’avoir une meilleure vision de la progression du dialogue, en prenant en compte la potentielle présence d’une incohérence dans son propre énoncé, c’est que nous appelons le double modèle du système, qui représente à la fois l’utilisateur et l’image que le système renvoie à l’utilisateur. Pour mettre en place ces fonctionnalités, nous exploitons les réseaux de mémoire de bout-en-bout, un modèle de réseau de neurones récurrent qui possède la spécificité non seulement de traiter des historiques de dialogue longs (comme un RNN ou un LSTM) mais également de créer des sauts de réflexion, permettant de filtrer l’information contenue à la fois dans l’énoncé de l’utilisateur et dans celui de l’historique de dialogue. De plus, ces trois sauts de réflexion servent de mécanisme d’attention “naturel” pour le réseau de mémoire, à la manière d’un décodeur de transformeur. Pour notre étude, nous améliorons, en y ajoutant nos trois fonctionnalités, un type de réseau de mémoire appelé WMM2Seq (réseau de mémoire de travail par séquence). Ce modèle s’inspire des modèles cognitifs de la mémoire, en présentant les concepts de mémoire épisodique, de mémoire sémantique et de mémoire de travail. Il obtient des résultats performants sur des tâches de génération de réponse de dialogue sur les corpus DSTC2 (humain-machine dans le domaine de restaurant) et MultiWOZ (multi-domaine créé avec Magicien d’Oz); ce sont les corpus que nous utilisons pour nos expériences. Les trois axes mentionnés précédemment apportent deux contributions principales à l’existant. En premier lieu, ceci complexifie l’intelligence du système de dialogue en le dotant d’un garde-fou (incohérences détectées). En second lieu, cela optimise à la fois le traitement des informations dans le dialogue (réponses plus précises ou plus riches) et la durée de celui-ci. Nous évaluons les performances de notre système avec premièrement la f-mesure pour les entités détectées à chaque tour de parole, deuxièmement de score BLEU pour la fluidité de l’énoncé du système et troisièmement de taux d’exactitude jointe pour la réussite du dialogue. Les résultats obtenus montrent l’intérêt d’orienter les recherches vers des modèles de gestion de la mémoire plus cognitifs afin de réduire l’écart de performance dans un dialogue entre l’humain et la machineIn this work, we are interested in the place of task-oriented dialogue systems in both automatic language processing and human-machine interaction. In particular, we focus on the difference in information processing and memory use, from one turn to the next, by humans and machines, during a written chat conversation. After having studied the mechanisms of memory retention and recall in humans during a dialogue, in particular during the accomplishment of a task, we hypothesize that one of the elements that may explain why the performance of machines remains below that of humans, is the ability to possess not only an image of the user, but also an image of oneself, explicitly summoned during the inferences linked to the continuation of the dialogue. This translates into the following three axes for the system. First, by the anticipation, at a given turn of speech, of the next turn of the user. Secondly, by the detection of an inconsistency in one's own utterance, facilitated, as we demonstrate, by the anticipation of the user's next turn as an additional cue. Finally, by predicting the number of remaining turns in the dialogue in order to have a better vision of the dialogue progression, taking into account the potential presence of an incoherence in one's own utterance, this is what we call the dual model of the system, which represents both the user and the image that the system sends to the user. To implement these features, we exploit end-to-end memory networks, a recurrent neural network model that has the specificity not only to handle long dialogue histories (such as an RNN or an LSTM) but also to create reflection jumps, allowing to filter the information contained in both the user's utterance and the dialogue history. In addition, these three reflection jumps serve as a "natural" attention mechanism for the memory network, similar to a transformer decoder. For our study, we enhance a type of memory network called WMM2Seq (sequence-based working memory network) by adding our three features. This model is inspired by cognitive models of memory, presenting the concepts of episodic memory, semantic memory and working memory. It performs well on dialogue response generation tasks on the DSTC2 (human-machine in the restaurant domain) and MultiWOZ (multi-domain created with Wizard of Oz) corpora; these are the corpora we use for our experiments. The three axes mentioned above bring two main contributions to the existing. Firstly, it adds complexity to the intelligence of the dialogue system by providing it with a safeguard (detected inconsistencies). Second, it optimizes both the processing of information in the dialogue (more accurate or richer answers) and the duration of the dialogue. We evaluate the performance of our system with firstly the F1 score for the entities detected in each speech turn, secondly the BLEU score for the fluency of the system utterance and thirdly the joint accuracy for the success of the dialogue. The results obtained show that it would be interesting to direct research towards more cognitive models of memory management in order to reduce the performance gap in a human-machine dialogue
8
Kowtko, J. C. "The function of intonation in task-oriented dialogue." Thesis, University of Edinburgh, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.508706.
Full text
9
Carletta, Jean. "Risk-taking and recovery in task-oriented dialogue." Thesis, University of Edinburgh, 1992. http://hdl.handle.net/1842/20370.
Full textAbstract:
The Principle of Parsimony states that by and large, agents try to complete tasks using as little effort as possible. This thesis demonstrates that the Principle of Parsimony operates in human task-oriented dialogue by showing the effects of Parsimony in a corpus of human dialogues about a map navigation task and by using the main points of the analysis in order to guide simulated conversations between two computer agents within the JAM system. It makes four major contributions: an analysis of 'communicative posture', or a range of choices in dialogue which can be characterised by decisions about how much effort to spend constructing one's utterances, leading to either careful or risky behaviour about different aspects of communication, an analysis of 'recovery strategies' which allow the participants to recover from failures which have been brought about due to risky postures, a heuristic model of belief which risks failing to capture the full meaning of the dialogue in favour of efficiency in a way which models human belief updating more plausibly than previous models, and a layered agent architecture which allows the simulated agents to make all of their decisions based on the Principle of Parsimony.
10
Sotillo, Catherine Frances. "Phonological reduction and intelligibility in task-oriented dialogue." Thesis, University of Edinburgh, 1997. http://hdl.handle.net/1842/21544.
Full textAbstract:
This thesis explores the implications of Lindblom's theory of Hyper- and Hypo-articulation (Lindblom, 1983, 1990) for word intelligibility and the likely application of phonological reduction processes in spontaneous discourse, using data from the HCRC Map Task Corpus. Lindblom claims that variability in articulatory clarity is a reflection of speakers' assessments of their listeners' information requirements: speakers hyper-articulate when listeners require maximum acoustic input from with information from other sources. To prevent speakers from over-economising to a point of unintelligibility, hypo-articulation is governed by a constraint of lexical distinctiveness: speakers hypo-articulate only while listeners are able to distinguish the target from competing lexical items. Three main questions are addressed. First, do the informational needs of the listener affect the articulatory clarity of words produced in spontaneous conversation? A series of intelligibility experiments shows that repeated mentions of landmark names are less intelligible than their introductory mentions, independent of which speaker utters either mention, and who can see the landmark on their map. Although the results can be interpreted as supporting Lindblom's view, textual Giveness (Prince, 1981) is shown to depend upon what the speaker knows, rather than what the speaker believes her listener to know. The reduction in clarity associated with an increase in available information is not necessarily listener-oriented as the H & H theory proposes. Secondly, do phonological processes such as word-final /d/-deletion or place assimilation contribute to intelligibility loss? Although reduction processes are found to be more prevalent in tokens from spontaneous discourse than in matched citation forms, they generally fail to account for effects of repetition. An increase in assimilation is found for repeated mentions of nasal-final stimuli in pre-velar position, but no effects is found for assimilation in pre-label position, or for word-final /d/-deletion, nor is an effect found for the duration of schwa in metrically Weak initial syllables of polysyllabic words.
11
Louvan, Samuel. "Low-Resource Natural Language Understanding in Task-Oriented Dialogue." Doctoral thesis, Università degli studi di Trento, 2022. http://hdl.handle.net/11572/333813.
Full textAbstract:
Task-oriented dialogue (ToD) systems need to interpret the user's input to understand the user's needs (intent) and corresponding relevant information (slots). This process is performed by a Natural Language Understanding (NLU) component, which maps the text utterance into a semantic frame representation, involving two subtasks: intent classification (text classification) and slot filling (sequence tagging). Typically, new domains and languages are regularly added to the system to support more functionalities. Collecting domain-specific data and performing fine-grained annotation of large amounts of data every time a new domain and language is introduced can be expensive. Thus, developing an NLU model that generalizes well across domains and languages with less labeled data (low-resource) is crucial and remains challenging.
This thesis focuses on investigating transfer learning and data augmentation methods for low-resource NLU in ToD. Our first contribution is a study of the potential of non-conversational text as a source for transfer. Most transfer learning approaches assume labeled conversational data as the source task and adapt the NLU model to the target task. We show that leveraging similar tasks from non-conversational text improves performance on target slot filling tasks through multi-task learning in low-resource settings. Second, we propose a set of lightweight augmentation methods that apply data transformation on token and sentence levels through slot value substitution and syntactic manipulation. Despite its simplicity, the performance is comparable to deep learning-based augmentation models, and it is effective on six languages on NLU tasks. Third, we investigate the effectiveness of domain adaptive pre-training for zero-shot cross-lingual NLU. In terms of overall performance, continued pre-training in English is effective across languages. This result indicates that the domain knowledge learned in English is transferable to other languages. In addition to that, domain similarity is essential. We show that intermediate pre-training data that is more similar – in terms of data distribution – to the target dataset yields better performance.
12
Davies, B. L. "An empirical examination of cooperation, effort and risk in task-oriented dialogue." Thesis, University of Edinburgh, 1997. http://hdl.handle.net/1842/18133.
Full textAbstract:
This thesis presents a discussion of proposed structuring principles for dialogue, and tests them empirically using data from the HCRC Map Task Corpus. The concepts of Cooperation (as described by Grice, and as used more generally in Linguistics), Coordination, Collaboration, Parsimony, Risk and Effort are ex¬ amined, and empirically testable hypotheses are developed, with which we are able to evaluate the claims for these principles in the context of task-oriented dialogue. In order to test our hypotheses, we categorise the utterances in our database in terms of Risk and Effort. Unlike Discourse Analysis, Conversation Analysis or Dialogue Games, our approach is evaluative. The intent in our dialogue coding is not only to label what the speakers did, but also to assess it in terms of its appropriateness at that point in the dialogue: the system codes not only what people do, but also what they don't do. Therefore, our system marks both the presence and absence of dialogue attributes. The hypotheses derived from the structuring concepts were statistically tested on the data produced by the coding system. The results produced by the empiri¬ cal tests showed a relationship between dialogue errors and task errors, but not between increased effort and increased task success. The importance of matched effort was also demonstrated, as dialogue pairs who invested similar amounts of effort produced better task results. Dialogue pairs also produced better results over time, which we argue is due to the focusing of effort. Participants work out where their effort should be channelled so that they can increase risk-taking where problems have not occurred, and decrease risk-taking where problems have occurred. These results suggest that interactants' behaviour follows a Principle of Least Individual Effort, which we argue subsumes the Principle of Parsimony and thus the Risk-Effort Trade-Olf. We reject the Principle of Least Collaborative Effort because although the empirical result of high effort not being associated with task success supports this principle in theory, we argue that its motivation is not supported in practice. The empirical work also distinguishes between what we term 'Gricean Cooperation', and folklinguistic notions of Cooperation found in the literature. In general terms, Gricean Cooperation predicted the same type of effort-minimising behaviour as the Principle of Least Individual Effort, and was thus supported by the empirical work. However, the concept of 'helpfulness' suggested by more general uses of Cooperation made predictions which were in conflict with those of the Principle of Least Individual Effort, and were found not to be supported.
13
Barange, Mukesh. "Task-oriented communicative capabilities of agents in collaborative virtual environments for training." Thesis, Brest, 2015. http://www.theses.fr/2015BRES0013/document.
Full textAbstract:
Les besoins croissants en formation et en entrainement au travail d’équipe ont motivé l’utilisationd’Environnements de réalité Virtuelle Collaboratifs de Formation (EVCF) qui permettent aux utilisateurs de travailler avec des agents autonomes pour réaliser une activité collective. L’idée directrice est que la coordination efficace entre les membres d’une équipe améliore la productivité et réduit les erreurs individuelles et collectives. Cette thèse traite de la mise en place et du maintien de la coordination au sein d’une équipe de travail composée d’agents et d’humains interagissant dans un EVCF.L’objectif de ces recherches est de doter les agents virtuels de comportements conversationnels permettant la coopération entre agents et avec l’utilisateur dans le but de réaliser un but commun.Nous proposons une architecture d’agents Collaboratifs et Conversationnels, dérivée de l’architecture Belief-Desire-Intention (C2-BDI), qui gère uniformément les comportements délibératifs et conversationnels comme deux comportements dirigés vers les buts de l’activité collective. Nous proposons un modèle intégré de la coordination fondé sur l’approche des modèles mentaux partagés, afin d’établir la coordination au sein de l’équipe de travail composée d’humains et d’agents. Nous soutenons que les interactions en langage naturel entre les membres d’une équipe modifient les modèles mentaux individuels et partagés des participants. Enfin, nous décrivons comment les agents mettent en place et maintiennent la coordination au sein de l’équipe par le biais de conversations en langage naturel. Afin d’établir un couplage fort entre la prise de décision et le comportement conversationnel collaboratif d’un agent, nous proposons tout d’abord une approche fondée sur la modélisation sémantique des activités humaines et de l’environnement virtuel via le modèle mascaret puis, dans un second temps, une modélisation du contexte basée sur l’approche Information State. Ces représentations permettent de traiter de manière unifiée les connaissances sémantiques des agents sur l’activité collective et sur l’environnement virtuel ainsi que des informations qu’ils échangent lors de dialogues.Ces informations sont utilisées par les agents pour la génération et la compréhension du langage naturel multipartite. L’approche Information State nous permet de doter les agents C2BDI de capacités communicatives leur permettant de s’engager pro-activement dans des interactions en langue naturelle en vue de coordonner efficacement leur activité avec les autres membres de l’équipe. De plus, nous définissons les protocoles conversationnels collaboratifs favorisant la coordination entre les membres de l’équipe. Enfin, nous proposons dans cette thèse un mécanisme de prise de décision s’inspirant de l’approche BDI qui lie les comportements de délibération et de conversation des agents. Nous avons mis en oeuvre notre architecture dans trois différents scénarios se déroulant dans des EVCF. Nous montrons que les comportements conversationnels collaboratifs multipartites des agents C2BDI facilitent la coordination effective de l’utilisateur avec les autres membres de l’équipe lors de la réalisation d’une tâche partagéeGrowing needs of educational and training requirements motivate the use of collaborative virtual environments for training (CVET) that allows human users to work together with autonomous agents to perform a collective activity. The vision is inspired by the fact that the effective coordination improves productivity, and reduces the individual and team errors. This work addresses the issue of establishing and maintaining the coordination in a mixed human-agent teamwork in the context of CVET. The objective of this research is to provide human-like conversational behavior of the virtual agents in order to cooperate with a user and other agents to achieve shared goals.We propose a belief-desire-intention (BDI) like Collaborative Conversational agent architecture(C2BDI) that treats both deliberative and conversational behaviors uniformly as guided by the goal-directed shared activity. We put forward an integrated model of coordination which is founded on the shared mental model based approaches to establish coordination in a human-agent teamwork. We argue that natural language interaction between team members can affect and modify the individual and shared mental models of the participants. Finally, we describe the cultivation of coordination in a mixed human-agent teamwork through natural language conversation. In order to establish the strong coupling between decision making and the collaborative conversational behavior of the agent, we propose first, the Mascaret based semantic modeling of human activities and the VE, and second, the information state based context model. This representation allows the treatment of semantic knowledge of the collaborative activity and virtual environment, and information exchanged during the dialogue conversation in a unified manner. This knowledge can be used by the agent for multiparty natural language processing (understanding and generation) in the context of the CEVT. To endow the communicative capabilities to C2BDI agent, we put forward the information state based approach for the natural language processing of the utterances. We define collaborative conversation protocols that ensure the coordination between team members. Finally, in this thesis, we propose a decision making mechanism, which is inspired by the BDI based approach and provides the interleaving between deliberation and conversational behavior of the agent. We have applied the proposed architecture to three different scenarios in the CVET. We found that the multiparty collaborative conversational behavior of C2BDI agent is more constructive and facilitates the user to effectively coordinate with other team members to perform a shared task
14
Golby, Christopher. "User-centred design of a task-oriented upper-limb assessment system for stroke." Thesis, University of Warwick, 2015. http://wrap.warwick.ac.uk/72926/.
Full textAbstract:
During rehabilitation from Stroke, patients require assessment of their upper-limb motor control. Outcome measures can often be subjective and objective data is required to supplement therapist/patient opinion on progress. This can be performed through goniometry; however, goniometry can be time-consuming, have inaccuracies of ±23º, and is therefore, often not used. Motion tracking technology is a possible answer to this problem, but can also be costly, time-consuming and not suitable for the clinical environment. This thesis aims to provide an objective, digital intervention method for assessing range of motion to supplement current outcome measures which is suitable for the clinical environment. This was performed by creating a low-cost technology through a user-centred design approach. Requirements elicitation demonstrated that a motivational, portable, cost-effective, non-invasive, time saving system for assessing functional activities was needed. Therefore, a system which utilised a Microsoft Kinect and EZ430 chronos wrist watch to track patient’s movements during and/or outside of therapy sessions was created. Measurements can be taken in a matter of minutes and provide a high quantity of objective data regarding patient movement. The system was verified, using healthy volunteers, by showing similar error rates in the system across 3 weeks in 10 able-bodied individuals, with error rates produced by a physiotherapist using goniometry. The system was also validated in the clinical setting with 6 stroke patients, over 15 weeks, as selected by 6 occupational therapists and 3 physiotherapists in 2 NHS stroke wards. The approach which has been created in this thesis is objective, repeatable, low-cost, portable, and non-invasive; allowing it to be the first tool for the objective assessment of upper-limb ROM which is efficiently designed and suitable for everyday use in stroke rehabilitation.
15
Baggs, Edward. "Acting in a populated environment : an ecological realist enquiry into speaking and collaborating." Thesis, University of Edinburgh, 2015. http://hdl.handle.net/1842/16200.
Full textAbstract:
The thesis seeks to develop an account of collaborative activities within the framework of ecological realism—an approach to psychology developed by James J. Gibson in the course of work on visual perception. Two main questions are addressed; one ontological, and one methodological. The ontological question is: given that collaborative activities take place within an environment, what kinds of structure must this environment contain? The response emphasizes the importance of relations which exist between entities, and which connect a given perceiver-actor with the other objects and individuals in its surroundings, and with the relations between those entities. It is held that activities take place within a field of relations. This description draws on the radical empiricist doctrine that relations are real, are external, and are directly perceivable. The present proposal insists that, in addition to being directly perceivable, relations can also be directly acted upon: throwing a ball for a dog is acting on a relation between dog and ball in space. The relational field account of collaboration naturally extends to an account of speaking: people, through their history of acting in an environment populated by other speakers, come to stand in a set of relations with objects and events around them, and these relations can be directly acted upon by others through the use of verbal actions. Verbal actions serve to direct the attention of others to relevant aspects of the environment, and this allows us as speakers to coordinate and manage one another’s activity. The methodological question is this: granting that the environment may be structured as a field of relations, how are we to conduct our empirical investigations, such that we can ask precise questions which lead to useful insights about how a given collaborative activity is carried out in practice? The central issue here concerns the concept of the task. Psychologists are in the habit of using this term quite loosely, to denote the actions of an individual or a group, in a laboratory or outside. This creates confusion in discussions of collaborative phenomena: who is the agent of a ‘collaborative task’? The definition offered here states that a task is a researcher-defined unit of study that corresponds to a change in the structure of the environment that has a characteristic pattern and that is meaningful from the first-person perspective of a particular actor. On this definition, the task is a tool that allows ecological psychologists to carve up the problem space into specific, tractable questions; the task is the equivalent of the cognitivist’s mental module. Task-oriented psychology encourages us to ask the question: which specific resources is the individual making use of in controlling this particular activity? The methodology is developed through an examination of the alarm calling behaviour of vervet monkeys, which is explained in terms of actions on the relational field, and through an analysis of corpus data from a laboratory-based collaborative assembly game. The relational field model promises to provide a way of studying social and collaborative activities on ecological realist principles. The concluding chapter identifies two particular areas in which the model might fruitfully be developed: in the study of learning, and in the theory of designing objects and spaces for interaction.
16
Canducci, Marco. "End-to-End Goal-Oriented Conversational Agent for Risk Awareness." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20381/.
Full textAbstract:
Traditional development of goal-oriented conversational agents typically require a lot of domain-specific handcrafting, which precludes scaling up to different domains; end-to-end systems would escape this limitation because they can be trained directly from dialogues. The very promising success recently obtained in end-to-end chatbots development could carry over to goal-oriented settings: applying deep learning models for building robust and scalable goal-oriented dialog systems directly from corpora of conversations is a challenging task and an open research area. For this reason, I decided that it would have been more relevant in the context of a master's thesis to experiment and get acquainted with these new promising methodologies - although not yet ready for production - rather than investing time in hand-crafting dialogue rules for a domain-specific solution. My thesis work had the following macro objectives: (i) investigate the latest research works concerning goal-oriented conversational agents development; (ii) choose a reference study, understand it and implement it with an appropriate technology; (iii) apply what learnt to a particular domain of interest. As a reference framework I chose the end-to-end memory networks (MemN2N) (Sukhbaatar et al., 2015) because it has proven to be particularly promising and has been used as a baseline for many recent works. Not having real dialogues available for training though, I took care of synthetically generating a corpora of conversations, taking a cue from the Dialog bAbI dataset for restaurant reservations (Bordes et al., 2016) and adapting it to the new domain of interest of risk awareness. Finally, I built a simple prototype which exploited the pre-trained dialog model in order to advise users about risk through an anthropomorphic talking avatar interface.
17
Smith, Jill Yvonne. "Communication Quality in Information Systems Development: The Effect of Computer-Mediated Communication on Task-Oriented Problem Solving." Thesis, North Texas State University, 1986. https://digital.library.unt.edu/ark:/67531/metadc331600/.
Full textAbstract:
The problem motivating this research is that ineffective communication may hamper systems development efforts. Specifically germane to this study are development efforts characterized as task-oriented, and which require information-sharing and problem-solving activities. This research problem motivated an analysis of the communication process and lead to the development of a temporal framework that delineates variables associated with task-oriented, end user/systems analyst communication interactions. Several variables within this framework are depicted in two theoretical models. The first model shows the theoretical relationship between an independent variable, communication mode (represented by asynchronous computer conferencing and face-to-face conferencing), and five dependent variables: (1) the amount of information shared, (2) the significance of the information shared, (3) the comprehensiveness of the information shared, (4) the perception of progress toward the goal, and (5) the perception of freedom to participate. The second model depicts the assumed interaction between communication mode, the five variables cited above (now acting as independent variables), and a dependent variable, communication quality. There are two theoretical components of communication quality: (1) deviation from an optimal set of user requirements, and (2) the degree of convergence (unity based on mutual understanding and mutual agreement) emanating from a communication interaction. Using the theoretical models as a guide, an experiment was designed and performed to test the relationships among the variables. The experimental results led to the rejection of all null hypotheses; the results strongly favored face-to-face conferencing for solving task-oriented, information-sharing problems analagous to the case used in the present study. The findings indicate that asynchronous computer conferencing may have a detrimental effect on the thoroughness of information exchange, on the relevance of the information shared in terms of making the correct decision, and on the completeness of the consideration given to all problem dimensions.
18
de, la Vara González José Luis. "Business process-based requirements specification and object-oriented conceptual modelling of information systems." Doctoral thesis, Universitat Politècnica de València, 2011. http://hdl.handle.net/10251/11445.
Full textAbstract:
Two of the main needs when developing an information system for an
organization are that system analysts know and understand the
application domain and that the system properly supports the business
processes of the organization. Consequently, elicitation of system
requirements from business process models has been acknowledged as a
suitable activity to deal with that needs. In addition, system requirements
must be linked to subsequent development stages.
However, system analysts can face many challenges when
performing these activities. They may have problems communicating
with customer stakeholders and may need to analyse and operationalize
the purpose of the information system. Furthermore, system analysts
must bridge the gap between business and system domains for
specification of system requirements, specify different types of system
requirements and guarantee that their specification is precise, consistent
and homogeneous.
In relation to object-oriented conceptual modelling-based
information system development, system analysts must also avoid
potential problems that may arise when a conceptual schema is created
from system requirements as part of their link with subsequent
development stages. For example, a conceptual schema can be
incomplete and/or inconsistent if it is not properly managed.
As a solution, this thesis presents a methodological approach for
business process-based requirements specification and object-oriented
conceptual modelling of information systems. The approach consists of
four stages: organizational modelling, purpose analysis, specification of
system requirements and derivation of object-oriented diagrams.
By following the design research methodology for performing
research in information systems, the methodological approach has been
designed on the basis of many existing ideas and principles in academia
and industry and provides new principles, mechanisms and guidance to
address the challenges presented above.De La Vara González, JL. (2011). Business process-based requirements specification and object-oriented conceptual modelling of information systems [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/11445
Palancia
19
Lee, John Ray. "Conversations with an intelligent agent-- modeling and integrating patterns in communications among humans and agents." Diss., University of Iowa, 2006. http://ir.uiowa.edu/etd/61.
Full text
20
Owaied, H. H. "A computer assisted learning system for reliability engineering : A PROLOG-oriented model devised for the acquisition of domain specific knowledge using a subset of English language dialogue and cognitive psychology principles." Thesis, University of Bradford, 1988. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.381436.
Full text
21
Benhalima, Djamel-Eddine. "Contribution à la conception d'un système d'analyse expérimentale SICOPE fondée sur une approche orientée-objet : Application à la communication graphique." Valenciennes, 1995. https://ged.uphf.fr/nuxeo/site/esupversions/3eea74bf-26cc-473d-9ec6-11405b54fb6c.
Full textAbstract:
Le succès de l'analyse expérimentale dans des domaines aussi complexes que la communication graphique fait croitre encore plus le besoin en expérimentations. Or l'élaboration d'un protocole expérimental est une tâche difficile, vu la quantité considérable de paramètres mis en jeu et la multiplicité des critères d'optimisation. Cependant, il existe peu d'outils tels qu'une méthodologie, un système d'aide, qui permettent d'aider les expérimentateurs. Il serait illusoire, en effet, de penser que l'analyse expérimentale est entrée dans sa phase de maturité, car de nombreux problèmes d'ordre méthodologique et d'outils aptes à apporter une aide réelle au processus d'élaboration de protocoles expérimentaux restent posés. L'objectif de ce mémoire est de proposer d'une part, une méthodologie d'étude expérimentale et d'autre part, un système interactif de conception de protocoles expérimentaux SICOPE
22
MEDEIROS, Francisco Petrônio Alencar de. "Projeto e implementação de módulo TAOS-Graph da ferramenta iTAOS para análise e modelagem da tarefa." Universidade Federal de Campina Grande, 2003. http://dspace.sti.ufcg.edu.br:8080/jspui/handle/riufcg/1557.
Full textAbstract:
Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-08-27T17:05:09Z
No. of bitstreams: 1
FRANCISCO PETRÔNIO ALENCAR DE MEDEIROS - DISSERTAÇÃO PPGCC 2003..pdf: 3495874 bytes, checksum: 26f2cedd183b05f7571147e29242352b (MD5)Made available in DSpace on 2018-08-27T17:05:09Z (GMT). No. of bitstreams: 1 FRANCISCO PETRÔNIO ALENCAR DE MEDEIROS - DISSERTAÇÃO PPGCC 2003..pdf: 3495874 bytes, checksum: 26f2cedd183b05f7571147e29242352b (MD5) Previous issue date: 2003-02-26
Esse trabalho apresenta o processo de construção e implementação do módulo TAOSGraph da ferramenta iTAOS. iTAOS é uma ferramenta gráfica que implementa o formalismo TAOS (Task and Action Oriented System) concebida para acompanhar o projetista de interfaces durante a fase de análise e descrição da tarefa dentro de um processo de desenvolvimento de interfaces, verificando a completude e consistência da representação. TAOS-Graph foi desenvolvido utilizando a metodologia MEDITE, uma metodologia guiada por modelos e baseada na tarefa para construção de interfaces ergonômicas. Os artefatos gerados ao final de cada etapa do processo de desenvolvimento de TAOS-Graph foram: a descrição TAOS da tarefa, a especificação conceitual da interação e o código da interface. Como recomenda a metodologia, foi realizada uma inspeção de conformidade da ferramenta iTAOS com as partes 14 (Menus), 16 (Manipulação direta) e 17 (Formulários) do padrão ISO 9241.
This work presents the process of construction and implementation of the TAOSGraph module of the iTAOS tool. iTAOS is a graphical tool that implements the TAOS formalism (Task and Action Oriented System) and is responsible for accompanying the interface designer (iTAOS user) during domain task’s description and analysis phases within the interface development process, verifying the completeness and the consistency of the representation. TAOS-Graph was developed using the methodology MEDITE, a methodology guided for models and based in the task for construction of ergonomic interfaces. The artefacts generated to the end of each stage of the development process of TAOS-Graph had been: description TAOS of the task, the conceptual specification of the interaction and the code of the interface. As recommends the methodology, iTAOS was carried through an inspection of conformity with the parts 14, 16 and 17 of the standard ISO 9241.
23
Wengerd, Lauren Rachel. "Advancing Rehabilitation Research Through Characterization of Conventional Occupational Therapy for Adult Stroke Survivors with Upper Extremity Hemiparesis." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu1574743933864793.
Full text
24
Mgijima-Msindwana, Mirriam Miranda Nomso. "Implementing Educational Innovations: The case of the Secondary School Curriculum Diversification Programme in Lesotho." University of the Western Cape, 1991. http://hdl.handle.net/11394/8434.
Full textAbstract:
Philosophiae Doctor - PhDBetween 1974 and 1982 the MOE introduced in two phases the diversification programme [SSCDP] which sought to establish practical subjects in the secondary school curriculum. This study examines the sustainability of implementation efforts beyond project expiry. It was hypothesised that SSCDP is not working as originally intended. The broad research problem was framed thus: What implementation response arises from an open-ended innovation policy? Subsidiary questions are: 1. How far have the policy-makers communicated the meaning of SSCDP and what factors account for mismatches between policy intentions and innovation practice? 2. What is the response of Project schools and what factors explain variation in response? 3. What is their significance for the sustainability of SSCDP? The analysis draws key concepts from the innovation literature on models and strategies of planned change; relationships in the implementation hierarchy; determinants of and orientations to the implementation process. Centred around qualitative research methods, the investigation utilises data from project documents, semi-structured interviews and from observations during school visits. Findings show an overall low level of implementation that varies among project schools. This is attributed to: Poor interpretation of SSCDP goals; Deficiencies in the implementation management; Idiosyncratic school behaviours. The study concludes that the 'practitioner-policy-maker' discrepancy is significant, hence the gap between policy intents and innovation practice. The gap is not regarded so much as an ultimate failure of the programme but as a necessary condition that allows for mutual adaptation between the innovation and its setting. This is reflected in the varied patterns of implementation response, classified as the: faithful; negotiators; selective adaptors; expansionists; and reductionist. As a policy-oriented study aiming at providing an 'improvement value', the findings lead to a proposal of improvements in the strategies of managing change in three areas: shifting focus from an adoption to an implementation perspective. Recognising implementation as a process dependent on a mutual linkage relationship among participants. Recognising schools as important bearers of change. These three are crucial factors in the implementation-sustainability relationship.
25
伊藤, 和明, Kazuaki Ito, 由紀子 山口, Yukiko Yamaguchi, 信夫 河口, Nobuo Kawaguchi, 茂樹 松原, Shigeki Matsubara, 康善 稲垣, and Yasuyoshi Inagaki. "拡張性を備えたオープンな電話対話システム開発ツールTEDDI." 情報処理学会, 2002. http://hdl.handle.net/2237/6885.
Full text
26
Kao, Shuo-Hung, and 高碩宏. "Antifire-bot:Intelligent Task-Oriented Dialogue System for Conflagration Evacuation." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/4976jw.
Full textAbstract:
碩士國立交通大學
土木工程系所
106
In this study, an attempt was made to develop a conversational bot for assisting people evacuate in case of fire. Whether civilians could adequately evacuate in the event of a fire depends on the dynamics between their behavior and the characteristics of buildings and burning fires. When a fire occurs, people have limited knowledge about fire, which makes it difficult to assess the scenario in time while the fire is spreading. However, it is of paramount importance whether people can effectively escape within a limited time and space. In this study, an evacuation decision-making model is proposed, based on literature review on evacuation simulations based on pedestrian flow correlation theory the experience of fire survival experts. Moreover, the interaction between the evacuation decision-making model, dialogue-based system, decision tree recommendation method, and the applicability and limitation of the human-computer interaction mode are discussed. Under the limitation mode of human-computer interaction, this study used the time of evacuation as the main limitation of successful escape. Using Natural Language Processing and Conversational User Interfaces, Messenger was used as a platform to explore the impact of dialogue-type robots on fire evacuee patterns in the event of fire. It is hoped that the results of this study will be useful for establishing or reviewing guidelines or standard procedures for fire evacuation and fire drills.
27
Lee, Chih-Wei, and 李致緯. "Improved Task-Oriented and Non-Task-Oriented Dialogue Systems: Language Learning Dialogue Game and Chatbot as Examples." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/ykwseq.
Full text
28
DeVault, David. "Contribution tracking participating in task-oriented dialogue under uncertainty." 2008. http://hdl.rutgers.edu/1782.2/rucore10001600001.ETD.17459.
Full text
29
Lopes, Nuno Tiago Tavares. "Privacy-oriented Task Orchestration System for IoT Networks." Master's thesis, 2021. https://hdl.handle.net/10216/135475.
Full text
30
Lopes, Nuno Tiago Tavares. "Privacy-oriented Task Orchestration System for IoT Networks." Dissertação, 2021. https://hdl.handle.net/10216/135475.
Full text
31
Kim, Joong Nam. "An agent-based cockpit task management system : a task-oriented pilot-vehicle interface." Thesis, 1994. http://hdl.handle.net/1957/35306.
Full text
32
WU, JIAN-CHANG, and 吳建昌. "The design of a semi-task-oriented robot programming system." Thesis, 1986. http://ndltd.ncl.edu.tw/handle/81910765457555663428.
Full text
33
Chang, Ku-Yaw, and 張顧耀. "A Pattern-Oriented Medical Imaging System And Its Task Guide." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/rr3skh.
Full textAbstract:
博士國立成功大學
電機工程學系碩博士班
90
Research in three-dimensional(3D) medical imaging has its roots in the 1970s, and has now been used clinically. At National Cheng-Kung University, we have been developed an interactive medical imaging system called Discover, which provides not only two-dimensional(2D) and 3D imaging analysis and generation functions, but also the function of interpolating 2D images to produce 3D data. Although the domain algorithms are very important, we also believe a well-structured system architecture is a key element of our system’s continuous growth. Meanwhile, it remains an important topic to help physicians use such an advanced and complex system like Discover. In this thesis, we first propose a new object interpolation method called multi-tuple interpolation, whose main feature is to take the global information of a real 3D object into consideration. Experiments on both synthetic and real medical images demonstrate our new approach can provide better results. We also introduce the Document-View-Presentation pattern, which is the basis of Discover’s system architecture, and describe how other constituent patterns are interwoven with each other. Our experience shows that the reusability and generalization of command objects do help reduce our maintenance efforts. Finally, we propose the ‘task guide’ concept to help use a complex application system, and implement this idea in Discover. A task guide is in essence an HTML document, which records a user’s steps of accomplishing a particular task. Other users can refer to the recorded steps of a task guide, and use this guide as a kind of user interface to work on other similar tasks. The same idea and its underlying mechanisms, i.e. HyperControl and HyperRecord, can also be applied to a variety of applications.
34
Khankan, K. "TOMRAS : a Task Oriented Mobile Remote Access System for desktop applications." Thesis, 2009. http://hdl.handle.net/10453/30186.
Full textAbstract:
University of Technology, Sydney. Faculty of Engineering and Information Technology.Mobile remote access to desktop applications is a potential enabler to improving the productivity and convenience of individuals and businesses. There is an increasing research interest in developing mobile remote access solutions for desktop applications. The developed proposals, however, are challenged by the hardware limitations of most mobile devices, such as the small display size. These limitations have a direct impact on the way existing desktop applications are presented on mobile devices. This thesis focuses on developing new ways of achieving effective mobile remote access to existing desktop applications. A conceptual model and implementation architecture for a task-oriented mobile remote access system (TOMRAS) have been introduced. The TOMRAS model adopts a user interface refactoring approach to generate task-oriented user interfaces for existing desktop applications without re-developing or modifying these applications. TOMRAS has a number of novel aspects, including, inferring user interface and behaviour knowledge from existing applications and transparently exposing the functionalities of existing desktop applications to be remotely accessible via a wide spectrum of mobile devices and platforms without redeveloping these desktop applications. The TOMRAS strategy of decoupling the generated mobile task's user interface from the functionality of existing applications also allows for a possible enriching of the mobile task's user interface with multimodal interaction capabilities. The thesis describes the TOMRAS conceptual model, and a potential implementation architecture for this model. The proposed implementation architecture articulates the intrinsic building blocks for mobile remote access solutions that adopt the TOMRAS model. The limitations of how widely and generically the model and techniques can be applied are also detailed in the thesis. Furthermore, a prototype that validates the feasibility of the TOMRAS implementation architecture is provided, and an evaluation of the effectiveness of the task-oriented approach is presented.
35
Chung, Kai-Hsin, and 鍾凱心. "A Study of Implementing a Task and Event Oriented Knowledge Management System." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/87737428639902385834.
Full textAbstract:
碩士國立交通大學
管理學院資訊管理學程
100
In today's knowledge economy era, the organization's most important assets are no longer just raw materials, manpower or equipment, but "knowledge". Knowledge determines the core competitiveness of enterprises, but without the systematic and effective management of the knowledge, an organization remains vulnerable to the loss of many valuable experiences. Business organizations actively import and construct knowledge management systems. A good knowledge management system will effectively enhance organizational value and capabilities. This study contains this scholar's opinions regarding the implementation of knowledge management success factors, supported by related documents. The focus is on the use of knowledge management processes: knowledge acquisition, knowledge sharing and knowledge utilization. The process includes the stage of the PDCA management cycle combination and induction of a knowledge management system architecture in order to assist organizations in their accumulation and the creation of valuable knowledge; this system is a task and event oriented. The case pilot company’s IT department is an appropriate knowledge management environment where the employees facilitate knowledge creation and exchange, through the work management series, to store organizational knowledge and save employees' work experience as well as organizational information and events. Final systematic performance evaluation of knowledge management systems regards the effectiveness of the information department of the case company gradually emerges, regarding the enhancement of the system effectiveness, reduction of operational costs and optimization of human use. The results can serve as future reference for enterprises’ knowledge management to have a positive evaluation.
36
Wu, Kuan-Hsing, and 吳冠興. "Implementing Task-Oriented Conversation System to Assist Language Learning - A Study on English Teaching System." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/5rjs8p.
Full textAbstract:
碩士中原大學
資訊管理研究所
107
This study improves the scoring mechanism of the Task-Oriented dialogue system, the goal is to improve the context of the dialogue system, including natural language processing, natural language understanding, and dialog state tracker module. Make the dialogue system more accurate find best response sentences, experiment with a mechanism similar to the teacher scoring mechanism. dialogue system can communicate with the machine and can be divided into Task-Oriented and Non-Task-Oriented, this study explores task orientation. Previous research has shown that Computer Assisted Instruction is effective for language learning, can assist teachers help learners enhance English speaking ability, simulate conversation situation, after the learners continuous to practice, improve conversational fluency and confidence. This study developed a system of Task-Oriented dialogue assisted language learning, Rule-based model design, provides learners with a game-based learning experience. Dialogue tree is designed by a professional English teacher, contain food, transportation, etc., scripts. Learners can easily talk to the system, because this study, imported a language model into dialogue management module. When the learner say different sentences will get different responses and scoring. This study proposes three different ways to predict scores, and evaluation is similar to teacher scoring. The research target is a college student in Chung Yuan Christian University, Department of Applied Linguistics and Language Studies, using the three-stage teaching steps proposed by Willis in 1996. Make the learner familiar with the system and task description before the teaching experiment, the teacher is the observer during the experiment, after the task is over, the learner will get a rating from the system and the teacher. This study proposes three different ways to scoring mechanism, evaluation method includes Root Mean Squared Error and Mean Absolute Error. minimum Mean Absolute Error is system scoring, but minimum Root Mean Square Error is the machine learning prediction scores. The contribution of this research is to developed a Task-Oriented dialogue assisted language learning system, it is not limited by time and place, according to this framework, can develop systems for other language learning.
37
Larson, Victoria M. "Task-Oriented, Naturally Elicited Speech (TONE) database for the Force Requirements Expert System, Hawaii (FRESH)." Thesis, 1988. http://hdl.handle.net/10945/23420.
Full text
38
Sankar, Chinnadhurai. "Neural approaches to dialog modeling." Thesis, 2020. http://hdl.handle.net/1866/24802.
Full textAbstract:
Cette thèse par article se compose de quatre articles qui contribuent au domaine de l’apprentissage profond, en particulier dans la compréhension et l’apprentissage des ap- proches neuronales des systèmes de dialogue. Le premier article fait un pas vers la compréhension si les architectures de dialogue neuronal couramment utilisées capturent efficacement les informations présentes dans l’historique des conversations. Grâce à une série d’expériences de perturbation sur des ensembles de données de dialogue populaires, nous constatons que les architectures de dialogue neuronal couramment utilisées comme les modèles seq2seq récurrents et basés sur des transformateurs sont rarement sensibles à la plupart des perturbations du contexte d’entrée telles que les énoncés manquants ou réorganisés, les mots mélangés, etc.
Le deuxième article propose d’améliorer la qualité de génération de réponse dans les systèmes de dialogue de domaine ouvert en modélisant conjointement les énoncés avec les attributs de dialogue de chaque énoncé. Les attributs de dialogue d’un énoncé se réfèrent à des caractéristiques ou des aspects discrets associés à un énoncé comme les actes de dialogue, le sentiment, l’émotion, l’identité du locuteur, la personnalité du locuteur, etc.
Le troisième article présente un moyen simple et économique de collecter des ensembles de données à grande échelle pour modéliser des systèmes de dialogue orientés tâche. Cette approche évite l’exigence d’un schéma d’annotation d’arguments complexes. La version initiale de l’ensemble de données comprend 13 215 dialogues basés sur des tâches comprenant six domaines et environ 8 000 entités nommées uniques, presque 8 fois plus que l’ensemble de données MultiWOZ populaire.This thesis by article consists of four articles which contribute to the field of deep learning, specifically in understanding and learning neural approaches to dialog systems. The first article takes a step towards understanding if commonly used neural dialog architectures effectively capture the information present in the conversation history. Through a series of perturbation experiments on popular dialog datasets, wefindthatcommonly used neural dialog architectures like recurrent and transformer-based seq2seq models are rarely sensitive to most input context perturbations such as missing or reordering utterances, shuffling words, etc. The second article introduces a simple and cost-effective way to collect large scale datasets for modeling task-oriented dialog systems. This approach avoids the requirement of a com-plex argument annotation schema. The initial release of the dataset includes 13,215 task-based dialogs comprising six domains and around 8k unique named entities, almost 8 times more than the popular MultiWOZ dataset. The third article proposes to improve response generation quality in open domain dialog systems by jointly modeling the utterances with the dialog attributes of each utterance. Dialog attributes of an utterance refer to discrete features or aspects associated with an utterance like dialog-acts, sentiment, emotion, speaker identity, speaker personality, etc. The final article introduces an embedding-free method to compute word representations on-the-fly. This approach significantly reduces the memory footprint which facilitates de-ployment in on-device (memory constraints) devices. Apart from being independent of the vocabulary size, we find this approach to be inherently resilient to common misspellings.