Contents
Academic literature on the topic 'Systèmes de dialogue orientés tâche'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Systèmes de dialogue orientés tâche.'
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.
Dissertations / Theses on the topic "Systèmes de dialogue orientés tâche"
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 textTask-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
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 textIn 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
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 textDialogue 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
Louvet, Jean-Baptiste. "Collaboration humain-machine à l’aide de motifs dialogiques pour la réalisation d’une tâche complexe : application à la recherche d’information Modeling a collaborative task with social commitments." Thesis, Normandie, 2019. http://www.theses.fr/2019NORMIR13.
Full textThis thesis offers a conventional model of the structure of a human-machine collaborative task to design an interactive system helping a human performing complex tasks. More specifically, we focus on tasks whose resolution is highly opportunistic and can not be planned. We introduce a task representation model based on dialogue games, dialogue patterns making it possible to describe the interaction structure with sequences of conventionally acceptable dialogue acts. We organize these dialogue patterns in states, structures describing the expected behaviors from each interlocutor during the different sub-tasks of the collaborative task. These states group dialogue patterns together in a coherent set in regard to the sub-task they are associated to and enrich them with locally relevant rules. They make it possible to describe the effects of the execution of a dialogue pattern by the interlocutors in a given context of the task. The states are used by the system to link an utterance of the human to the current state of the dialogue and of the task and to take the initiative of behaviors relevant with the interaction and helpful for the task. The decisions taken by the system are based on the concept of maturity, a value associated to each state representing the system’s ability to take initiatives in this state. The decision model of the system is designed to be resilient and give as much freedom as possible to the user. This model is implemented in CoCoA, a system that collaborates with a human to assist him performing a complex task. From the study of a human-human dialogue corpus on a medical collaborative information retrieval task, we use our model to describe the task. This use case is implemented with CoCoA and an evaluation is performed by simulating a human user with an information need and varying its actions according to behaviors identified in the corpus
Wable, Thierry. "Processus interactifs dans le dialogue Homme/Machine analyse des images identitaires, de la tâche et des dysfonctionnements lors d'une interrogation de base de données bibliographiques." Rouen, 1998. http://www.theses.fr/1998ROUEL288.
Full textThis linguistic study is a contribution to research on man / machine interaction in the language field. Our work relies on the analysis of experimental simulated dialogues involving a user and a manachine during a bibliographic data base inquiry. The human being asks an interface designed to help him to get the desired information ; that is the general task of the machine. This task is in practice a set of subtasks contributing to the main task and acting as a driving force. But the speaker occasionally escapes from this initial communication target and moves to a subdialogue which may generate dysfunctions. We have produced a survey and a catalogue of these dysfunctions together with processes for correction and avoidance. In this way we demonstrate that the dysfunctions can act as a contributor to the main task of the system, hence they can make the interaction successful. We also define the specific characters of this dialogue and explain how sense, identifying images (especially the construction and the representation of the interlocutor) and discursive forms management all contribute to the main objective. The results of this contribution should allow a better understanding of the interactive processes of the man / machine dialogue in order to improve the interface and optimize its tasks. This improvement requires a more efficient way to take into account current oroblems in all communication processes
Sankar, Chinnadhurai. "Neural approaches to dialog modeling." Thesis, 2020. http://hdl.handle.net/1866/24802.
Full textThis 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.