Articles de revues : « Task-oriented dialogue »

1

Andreas, Jacob, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim et al. « Task-Oriented Dialogue as Dataflow Synthesis ». Transactions of the Association for Computational Linguistics 8 (septembre 2020) : 556–71. http://dx.doi.org/10.1162/tacl_a_00333.

Texte intégral

Résumé :

We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for reference and revision that reuse dataflow fragments from previous turns. Our graph-based state enables the expression and manipulation of complex user intents, and explicit metacomputation makes these intents easier for learned models to predict. We introduce a new dataset, SMCalFlow, featuring complex dialogues about events, weather, places, and people. Experiments show that dataflow graphs and metacomputation substantially improve representability and predictability in these natural dialogues. Additional experiments on the MultiWOZ dataset show that our dataflow representation enables an otherwise off-the-shelf sequence-to-sequence model to match the best existing task-specific state tracking model. The SMCalFlow dataset, code for replicating experiments, and a public leaderboard are available at https://www.microsoft.com/en-us/research/project/dataflow-based-dialogue-semantic-machines .

Styles APA, Harvard, Vancouver, ISO, etc.

2

Xiang, Lu, Junnan Zhu, Yang Zhao, Yu Zhou et Chengqing Zong. « Robust Cross-lingual Task-oriented Dialogue ». ACM Transactions on Asian and Low-Resource Language Information Processing 20, n^o 6 (30 novembre 2021) : 1–24. http://dx.doi.org/10.1145/3457571.

Texte intégral

Résumé :

Cross-lingual dialogue systems are increasingly important in e-commerce and customer service due to the rapid progress of globalization. In real-world system deployment, machine translation (MT) services are often used before and after the dialogue system to bridge different languages. However, noises and errors introduced in the MT process will result in the dialogue system's low robustness, making the system's performance far from satisfactory. In this article, we propose a novel MT-oriented noise enhanced framework that exploits multi-granularity MT noises and injects such noises into the dialogue system to improve the dialogue system's robustness. Specifically, we first design a method to automatically construct multi-granularity MT-oriented noises and multi-granularity adversarial examples, which contain abundant noise knowledge oriented to MT. Then, we propose two strategies to incorporate the noise knowledge: (i) Utterance-level adversarial learning and (ii) Knowledge-level guided method. The former adopts adversarial learning to learn a perturbation-invariant encoder, guiding the dialogue system to learn noise-independent hidden representations. The latter explicitly incorporates the multi-granularity noises, which contain the noise tokens and their possible correct forms, into the training and inference process, thus improving the dialogue system's robustness. Experimental results on three dialogue models, two dialogue datasets, and two language pairs have shown that the proposed framework significantly improves the performance of the cross-lingual dialogue system.

Styles APA, Harvard, Vancouver, ISO, etc.

3

Wanderley, Gregory Moro Puppi, Cesar Augusto Tacla, Jean-Paul A. Barthès et Emerson Cabrera Paraiso. « Knowledge discovery in task-oriented dialogue ». Expert Systems with Applications 42, n^o 20 (novembre 2015) : 6807–18. http://dx.doi.org/10.1016/j.eswa.2015.05.005.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

4

Yang, Fan, et Peter A. Heeman. « Initiative conflicts in task-oriented dialogue ». Computer Speech & ; Language 24, n^o 2 (avril 2010) : 175–89. http://dx.doi.org/10.1016/j.csl.2009.04.003.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

5

Zhu, Qi, Kaili Huang, Zheng Zhang, Xiaoyan Zhu et Minlie Huang. « CrossWOZ : A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset ». Transactions of the Association for Computational Linguistics 8 (juillet 2020) : 281–95. http://dx.doi.org/10.1162/tacl_a_00314.

Texte intégral

Résumé :

To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset. It contains 6K dialogue sessions and 102K utterances for 5 domains, including hotel, restaurant, attraction, metro, and taxi. Moreover, the corpus contains rich annotation of dialogue states and dialogue acts on both user and system sides. About 60% of the dialogues have cross-domain user goals that favor inter-domain dependency and encourage natural transition across domains in conversation. We also provide a user simulator and several benchmark models for pipelined task-oriented dialogue systems, which will facilitate researchers to compare and evaluate their models on this corpus. The large size and rich annotation of CrossWOZ make it suitable to investigate a variety of tasks in cross-domain dialogue modeling, such as dialogue state tracking, policy learning, user simulation, etc.

Styles APA, Harvard, Vancouver, ISO, etc.

6

Matsumoto, Kazuyuki, Manabu Sasayama et Taiga Kirihara. « Topic Break Detection in Interview Dialogues Using Sentence Embedding of Utterance and Speech Intention Based on Multitask Neural Networks ». Sensors 22, n^o 2 (17 janvier 2022) : 694. http://dx.doi.org/10.3390/s22020694.

Texte intégral

Résumé :

Currently, task-oriented dialogue systems that perform specific tasks based on dialogue are widely used. Moreover, research and development of non-task-oriented dialogue systems are also actively conducted. One of the problems with these systems is that it is difficult to switch topics naturally. In this study, we focus on interview dialogue systems. In an interview dialogue, the dialogue system can take the initiative as an interviewer. The main task of an interview dialogue system is to obtain information about the interviewee via dialogue and to assist this individual in understanding his or her personality and strengths. In order to accomplish this task, the system needs to be flexible and appropriate for detecting topic switching and topic breaks. Given that topic switching tends to be more ambiguous in interview dialogues than in task-oriented dialogues, existing topic modeling methods that determine topic breaks based only on relationships and similarities between words are likely to fail. In this study, we propose a method for detecting topic breaks in dialogue to achieve flexible topic switching in interview dialogue systems. The proposed method is based on multi-task learning neural network that uses embedded representations of sentences to understand the context of the text and utilizes the intention of an utterance as a feature. In multi-task learning, not only topic breaks but also the intention associated with the utterance and the speaker are targets of prediction. The results of our evaluation experiments show that using utterance intentions as features improves the accuracy of topic separation estimation compared to the baseline model.

Styles APA, Harvard, Vancouver, ISO, etc.

7

Zhang, Zheng, Minlie Huang, Zhongzhou Zhao, Feng Ji, Haiqing Chen et Xiaoyan Zhu. « Memory-Augmented Dialogue Management for Task-Oriented Dialogue Systems ». ACM Transactions on Information Systems 37, n^o 3 (20 juillet 2019) : 1–30. http://dx.doi.org/10.1145/3317612.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

8

Gravano, Agustín, Julia Hirschberg et Štefan Beňuš. « Affirmative Cue Words in Task-Oriented Dialogue ». Computational Linguistics 38, n^o 1 (mars 2012) : 1–39. http://dx.doi.org/10.1162/coli_a_00083.

Texte intégral

Résumé :

We present a series of studies of affirmative cue words—a family of cue words such as “okay” or “alright” that speakers use frequently in conversation. These words pose a challenge for spoken dialogue systems because of their ambiguity: They may be used for agreeing with what the interlocutor has said, indicating continued attention, or for cueing the start of a new topic, among other meanings. We describe differences in the acoustic/prosodic realization of such functions in a corpus of spontaneous, task-oriented dialogues in Standard American English. These results are important both for interpretation and for production in spoken language applications. We also assess the predictive power of computational methods for the automatic disambiguation of these words. We find that contextual information and final intonation figure as the most salient cues to automatic disambiguation.

Styles APA, Harvard, Vancouver, ISO, etc.

9

Young, Tom, Frank Xing, Vlad Pandelea, Jinjie Ni et Erik Cambria. « Fusing Task-Oriented and Open-Domain Dialogues in Conversational Agents ». Proceedings of the AAAI Conference on Artificial Intelligence 36, n^o 10 (28 juin 2022) : 11622–29. http://dx.doi.org/10.1609/aaai.v36i10.21416.

Texte intégral

Résumé :

The goal of building intelligent dialogue systems has largely been separately pursued under two paradigms: task-oriented dialogue (TOD) systems, which perform task-specific functions, and open-domain dialogue (ODD) systems, which focus on non-goal-oriented chitchat. The two dialogue modes can potentially be intertwined together seamlessly in the same conversation, as easily done by a friendly human assistant. Such ability is desirable in conversational agents, as the integration makes them more accessible and useful. Our paper addresses this problem of fusing TODs and ODDs in multi-turn dialogues. Based on the popular TOD dataset MultiWOZ, we build a new dataset FusedChat, by rewriting the existing TOD turns and adding new ODD turns. This procedure constructs conversation sessions containing exchanges from both dialogue modes. It features inter-mode contextual dependency, i.e., the dialogue turns from the two modes depend on each other. Rich dependency patterns such as co-reference and ellipsis are included. The new dataset, with 60k new human-written ODD turns and 5k re-written TOD turns, offers a benchmark to test a dialogue model's ability to perform inter-mode conversations. This is a more challenging task since the model has to determine the appropriate dialogue mode and generate the response based on the inter-mode context. However, such models would better mimic human-level conversation capabilities. We evaluate two baseline models on this task, including the classification-based two-stage models and the two-in-one fused models. We publicly release FusedChat and the baselines to propel future work on inter-mode dialogue systems.

Styles APA, Harvard, Vancouver, ISO, etc.

10

Gravano, Agustín, et Julia Hirschberg. « Turn-taking cues in task-oriented dialogue ». Computer Speech & ; Language 25, n^o 3 (juillet 2011) : 601–34. http://dx.doi.org/10.1016/j.csl.2010.10.003.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

11

Traum, David R., et Elizabeth A. Hinkelman. « CONVERSATION ACTS IN TASK-ORIENTED SPOKEN DIALOGUE ». Computational Intelligence 8, n^o 3 (août 1992) : 575–99. http://dx.doi.org/10.1111/j.1467-8640.1992.tb00380.x.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

12

Tiwari, Abhisek, Tulika Saha, Sriparna Saha, Shubhashis Sengupta, Anutosh Maitra, Roshni Ramnani et Pushpak Bhattacharyya. « A dynamic goal adapted task oriented dialogue agent ». PLOS ONE 16, n^o 4 (1 avril 2021) : e0249030. http://dx.doi.org/10.1371/journal.pone.0249030.

Texte intégral

Résumé :

Purpose Existing virtual agents (VAs) present in dialogue systems are either information retrieval based or static goal-driven. However, in real-world situations, end-users might not have a known and fixed goal beforehand for the task, i.e., they may upgrade/downgrade/update their goal components in real-time to maximize their utility values. Existing VAs are unable to handle such dynamic goal-oriented situations. Methodology Due to the absence of any related dialogue dataset where such choice deviations are present, we have created a conversational dataset called Deviation adapted Virtual Agent(DevVA), with the manual annotation of its corresponding intents, slots, and sentiment labels. A Dynamic Goal Driven Dialogue Agent (DGDVA) has been developed by incorporating a Dynamic Goal Driven Module (GDM) on top of a deep reinforcement learning based dialogue manager. In the course of a conversation, the user sentiment provides grounded feedback about agent behavior, including goal serving action. User sentiment appears to be an appropriate indicator for goal discrepancy that guides the agent to complete the user’s desired task with gratification. The negative sentiment expressed by the user about an aspect of the provided choice is treated as a discrepancy that is being resolved by the GDM depending upon the observed discrepancy and current dialogue state. The goal update capability and the VA’s interactiveness trait enable end-users to accomplish their desired task satisfactorily. Findings The obtained experimental results illustrate that DGDVA can handle dynamic goals with maximum user satisfaction and a significantly higher success rate. The interaction drives the user to decide its final goal through the latent specification of possible choices and information retrieved and provided by the dialogue agent. Through the experimental results (qualitative and quantitative), we firmly conclude that the proposed sentiment-aware VA adapts users’ dynamic behavior for its goal setting with substantial efficacy in terms of primary objective i.e., task success rate (0.88). Practical implications In real world, it can be argued that many people do not have a predefined and fixed goal for tasks such as online shopping, movie booking & restaurant booking, etc. They tend to explore the available options first which are aligned with their minimum requirements and then decide one amongst them. The DGDVA provides maximum user satisfaction as it enables them to accomplish a dynamic goal that leads to additional utilities along with the essential ones. Originality To the best of our knowledge, this is the first effort towards the development of A Dynamic Goal Adapted Task-Oriented Dialogue Agent that can serve user goals dynamically until the user is satisfied.

Styles APA, Harvard, Vancouver, ISO, etc.

13

WRIGHT, PETER. « Using Constraints and Reference in Task–oriented Dialogue ». Journal of Semantics 7, n^o 1 (1990) : 65–79. http://dx.doi.org/10.1093/jos/7.1.65.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

14

Carletta, Jean, et Christopher S. Mellish. « Risk-taking and recovery in task-oriented dialogue ». Journal of Pragmatics 26, n^o 1 (juillet 1996) : 71–107. http://dx.doi.org/10.1016/0378-2166(95)00046-1.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

15

Chen, Zhi, Yuncong Liu, Lu Chen, Su Zhu, Mengyue Wu et Kai Yu. « OPAL : Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue ». Transactions of the Association for Computational Linguistics 11 (2023) : 68–84. http://dx.doi.org/10.1162/tacl_a_00534.

Texte intégral

Résumé :

Abstract This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD). Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: Dialogue state tracker (DST) and response generator (RG). The dialogue state consists of the domain-slot-value triples, which are regarded as the user’s constraints to search the domain-related databases. The large-scale task-oriented dialogue data with the annotated structured dialogue state usually are inaccessible. It prevents the development of the pretrained language model for the task-oriented dialogue. We propose a simple yet effective pretraining method to alleviate this problem, which consists of two pretraining phases. The first phase is to pretrain on large-scale contextual text data, where the structured information of the text is extracted by the information extracting tool. To bridge the gap between the pretraining method and downstream tasks, we design two pretraining tasks: ontology-like triple recovery and next-text generation, which simulates the DST and RG, respectively. The second phase is to fine-tune the pretrained model on the TOD data. The experimental results show that our proposed method achieves an exciting boost and obtains competitive performance even without any TOD data on CamRest676 and MultiWOZ benchmarks.

Styles APA, Harvard, Vancouver, ISO, etc.

16

Jang, Youngsoo, Jongmin Lee et Kee-Eung Kim. « Bayes-Adaptive Monte-Carlo Planning and Learning for Goal-Oriented Dialogues ». Proceedings of the AAAI Conference on Artificial Intelligence 34, n^o 05 (3 avril 2020) : 7994–8001. http://dx.doi.org/10.1609/aaai.v34i05.6308.

Texte intégral

Résumé :

We consider a strategic dialogue task, where the ability to infer the other agent's goal is critical to the success of the conversational agent. While this problem can be naturally formulated as Bayesian planning, it is known to be a very difficult problem due to its enormous search space consisting of all possible utterances. In this paper, we introduce an efficient Bayes-adaptive planning algorithm for goal-oriented dialogues, which combines RNN-based dialogue generation and MCTS-based Bayesian planning in a novel way, leading to robust decision-making under the uncertainty of the other agent's goal. We then introduce reinforcement learning for the dialogue agent that uses MCTS as a strong policy improvement operator, casting reinforcement learning as iterative alternation of planning and supervised-learning of self-generated dialogues. In the experiments, we demonstrate that our Bayes-adaptive dialogue planning agent significantly outperforms the state-of-the-art in a negotiation dialogue domain. We also show that reinforcement learning via MCTS further improves end-task performance without diverging from human language.

Styles APA, Harvard, Vancouver, ISO, etc.

17

Liu, Qi, Lei Yu, Laura Rimell et Phil Blunsom. « Pretraining the Noisy Channel Model for Task-Oriented Dialogue ». Transactions of the Association for Computational Linguistics 9 (2021) : 657–74. http://dx.doi.org/10.1162/tacl_a_00390.

Texte intégral

Résumé :

Abstract Direct decoding for task-oriented dialogue is known to suffer from the explaining-away effect, manifested in models that prefer short and generic responses. Here we argue for the use of Bayes’ theorem to factorize the dialogue task into two models, the distribution of the context given the response, and the prior for the response itself. This approach, an instantiation of the noisy channel model, both mitigates the explaining-away effect and allows the principled incorporation of large pretrained models for the response prior. We present extensive experiments showing that a noisy channel model decodes better responses compared to direct decoding and that a two-stage pretraining strategy, employing both open-domain and task-oriented dialogue data, improves over randomly initialized models.

Styles APA, Harvard, Vancouver, ISO, etc.

18

ZENG, Ya, Li WAN, Qiuhong LUO et Mao CHEN. « A Hierarchical Memory Model for Task-Oriented Dialogue System ». IEICE Transactions on Information and Systems E105.D, n^o 8 (1 août 2022) : 1481–89. http://dx.doi.org/10.1587/transinf.2022edp7001.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

19

Mushin, Ilana, Lesley Stirling, Janet Fletcher et Roger Wales. « Discourse Structure, Grounding, and Prosody in Task-Oriented Dialogue ». Discourse Processes 35, n^o 1 (janvier 2003) : 1–31. http://dx.doi.org/10.1207/s15326950dp3501_1.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

20

Jiang, ZongLi, et Shuo Zhang. « Research on Task-oriented Dialogue Based on Modified Transformer ». Journal of Physics : Conference Series 1544 (mai 2020) : 012188. http://dx.doi.org/10.1088/1742-6596/1544/1/012188.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

21

Zhao, Zhengyu, Weinan Zhang, Wanxiang Che, Zhigang Chen et Yibo Zhang. « An Evaluation of Chinese Human-Computer Dialogue Technology ». Data Intelligence 1, n^o 2 (mai 2019) : 187–200. http://dx.doi.org/10.1162/dint_a_00007.

Texte intégral

Résumé :

The human-computer dialogue has recently attracted extensive attention from both academia and industry as an important branch in the field of artificial intelligence (AI). However, there are few studies on the evaluation of large-scale Chinese human-computer dialogue systems. In this paper, we introduce the Second Evaluation of Chinese Human-Computer Dialogue Technology, which focuses on the identification of a user's intents and intelligent processing of intent words. The Evaluation consists of user intent classification (Task 1) and online testing of task-oriented dialogues (Task 2), the data sets of which are provided by iFLYTEK Corporation. The evaluation tasks and data sets are introduced in detail, and meanwhile, the evaluation results and the existing problems in the evaluation are discussed.

Styles APA, Harvard, Vancouver, ISO, etc.

22

Ayedoun, Emmanuel, Yuki Hayashi et Kazuhisa Seta. « An authoring tool for task-oriented dialogue scenarios design in EFL context ». Research and Practice in Technology Enhanced Learning 18 (28 décembre 2022) : 027. http://dx.doi.org/10.58459/rptel.2023.18027.

Texte intégral

Résumé :

Computer-based conversational environments have been advocated as a promising approach for providing virtual, yet realistic opportunities for communication practice to second language learners. However, the high authoring costs of such environments continue to prevent their widespread diffusion and adoption. Furthermore, there is a limited set of authoring interfaces dedicated to making the creation of dialogue scenarios in the context of language learning easier. In this research, we present a dialogue scenario authoring system that could aid the rapid implementation of desirable dialogue scenarios, lowering the barrier to dialogue scenario authoring for non-programmers or even educators. To that end, we built a pseudo-versatile dialogue scenario authoring interface that enables the automatic generation of services-related dialogue scenarios by leveraging the common underlying structure of services (restaurant, hotel, travel planning, etc.) that appear to share a certain degree of similarity at the task level. Here, we describe the proposed system’s features and present the findings of an experimental evaluation study that suggests the usefulness of our approach to facilitating dialogue scenarios designed by people with no prior experience authoring dialogue systems components. According to an evaluation of the tool by a second language teaching expert, the proposed system might also foster second language teaching and learning by allowing both educators and learners to participate in the design of dialogue scenarios that are adapted to different levels of learners.

Styles APA, Harvard, Vancouver, ISO, etc.

23

MORIN, PHILIPPE, JEAN-PAUL HATON, JEAN-MARIE PIERREL, GUENTHER RUSKE et WALTER WEIGEL. « A MULTILINGUAL APPROACH TO TASK-ORIENTED MAN-MACHINE DIALOGUE BY VOICE ». International Journal of Pattern Recognition and Artificial Intelligence 02, n^o 03 (septembre 1988) : 573–88. http://dx.doi.org/10.1142/s0218001488000339.

Texte intégral

Résumé :

In the framework of man-machine communication, oral dialogue has a particular place since human speech presents several advantages when used either alone or in multimedia interfaces. The last decade has witnessed a proliferation of research into speech recognition and understanding, but few systems have been defined with a view to managing and understanding an actual man-machine dialogue. The PARTNER system that we describe in this paper proposes a solution in the case of task oriented dialogue with the use of artificial languages. A description of the essential characteristics of dialogue systems is followed by a presentation of the architecture and the principles of the PARTNER system. Finally, we present the most recent results obtained in the oral management of electronic mail in French and German.

Styles APA, Harvard, Vancouver, ISO, etc.

24

Fuad, Ahlam, et Maha Al-Yahya. « AraConv : Developing an Arabic Task-Oriented Dialogue System Using Multi-Lingual Transformer Model mT5 ». Applied Sciences 12, n^o 4 (11 février 2022) : 1881. http://dx.doi.org/10.3390/app12041881.

Texte intégral

Résumé :

Task-oriented dialogue systems (DS) are designed to help users perform daily activities using natural language. Task-oriented DS for English language have demonstrated promising performance outcomes; however, developing such systems to support Arabic remains a challenge. This challenge is mainly due to the lack of Arabic dialogue datasets. This study introduces the first Arabic end-to-end generative model for task-oriented DS (AraConv), which uses the multi-lingual transformer model mT5 with different settings. We also present an Arabic dialogue dataset (Arabic-TOD) and used it to train and test the proposed AraConv model. The results obtained are reasonable compared to those reported in the studies of English and Chinese using the same mono-lingual settings. To avoid problems associated with a small training dataset and to improve the AraConv model’s results, we suggest joint-training, in which the model is jointly trained on Arabic dialogue data and data from one or two high-resource languages such as English and Chinese. The findings indicate the AraConv model performed better in the joint-training setting than in the mono-lingual setting. The results obtained from AraConv on the Arabic dialogue dataset provide a baseline for other researchers to build robust end-to-end Arabic task-oriented DS that can engage with complex scenarios.

Styles APA, Harvard, Vancouver, ISO, etc.

25

Lao, Yadi, Weijie Liu, Sheng Gao et Si Li. « MDKB-Bot : A Practical Framework for Multi-Domain Task-Oriented Dialogue System ». Data Intelligence 1, n^o 2 (mai 2019) : 176–86. http://dx.doi.org/10.1162/dint_a_00010.

Texte intégral

Résumé :

One of the major challenges to build a task-oriented dialogue system is that dialogue state transition frequently happens between multiple domains such as booking hotels or restaurants. Recently, the encoderdecoder model based on the end-to-end neural network has become an attractive approach to meet this challenge. However, it usually requires a sufficiently large amount of training data and it is not flexible to handle dialogue state transition. This paper addresses these problems by proposing a simple but practical framework called Multi-Domain KB-BOT (MDKB-BOT), which leverages both neural networks and rule-based strategy in natural language understanding (NLU) and dialogue management (DM). Experiments on the data set of the Chinese Human-Computer Dialogue Technology Evaluation Campaign show that MDKB-BOT achieves competitive performance on several evaluation metrics, including task completion rate and user satisfaction.

Styles APA, Harvard, Vancouver, ISO, etc.

26

Gritta, Milan, Gerasimos Lampouras et Ignacio Iacobacci. « Conversation Graph : Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management ». Transactions of the Association for Computational Linguistics 9 (février 2021) : 36–52. http://dx.doi.org/10.1162/tacl_a_00352.

Texte intégral

Résumé :

Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in size con- sidering the complexity of the dialogues. Additionally, conventional training signal in- ference is not suitable for non-deterministic agent behavior, namely, considering multiple actions as valid in identical dialogue states. We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi- reference training and evaluation of non- deterministic agents. ConvGraph generates novel dialogue paths to augment data volume and diversity. Intrinsic and extrinsic evaluation across three datasets shows that data augmentation and/or multi-reference training with ConvGraph can improve dialogue success rates by up to 6.4%.

Styles APA, Harvard, Vancouver, ISO, etc.

27

Raut, Aritra, Abhisek Tiwari, Subrata Das, Sriparna Saha, Anutosh Maitra, Roshni Ramnani et Shubhashis Sengupta. « Reinforcing personalized persuasion in task-oriented virtual sales assistant ». PLOS ONE 18, n^o 1 (5 janvier 2023) : e0275750. http://dx.doi.org/10.1371/journal.pone.0275750.

Texte intégral

Résumé :

Purpose Existing task-oriented virtual agents can assist users with simple tasks like ticket booking, hotel reservations, etc. effectively and with high confidence. These virtual assistants, however, assume specific, predictable end-user behavior, such as predefined/servable objectives, which results in conversation failures in challenging situations, such as when goals are unavailable. Methodology Inspired by the practice and its efficacy, we propose an end-to-end framework for task-oriented persuasive dialogue generation that combines pre-training and reinforcement learning for generating context-aware persuasive responses. We utilize four novel rewards to improve consistency and repetitiveness in generated responses. Additionally, a meta-learning strategy has also been utilized to make the model parameters better for domain adaptation. Furthermore, we also curate a personalized persuasive dialogue (PPD) corpus, which contains utterance-level intent, slot, sentiment, and persuasion strategy annotation. Findings The obtained results and detailed analysis firmly establish the effectiveness of the proposed persuasive virtual assistant over traditional task-oriented virtual assistants. The proposed framework considerably increases the quality of dialogue generation in terms of consistency and repetitiveness. Additionally, our experiment with a few shot and zero-shot settings proves that our meta-learned model learns to quickly adopt new domains with a few or even zero no. of training epochs. It outperforms the non-meta-learning-based approaches keeping the base model constant. Originality To the best of our knowledge, this is the first effort to improve a task-oriented virtual agent’s persuasiveness and domain adaptation.

Styles APA, Harvard, Vancouver, ISO, etc.

28

Malviya, Shrikant, Rohit Mishra, Santosh Kumar Barnwal et Uma Shanker Tiwary. « HDRS : Hindi Dialogue Restaurant Search Corpus for Dialogue State Tracking in Task-Oriented Environment ». IEEE/ACM Transactions on Audio, Speech, and Language Processing 29 (2021) : 2517–28. http://dx.doi.org/10.1109/taslp.2021.3065833.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

29

Huang, Jhih-Yuan, Wei-Po Lee, Chen-Chia Chen et Bu-Wei Dong. « Developing Emotion-Aware Human–Robot Dialogues for Domain-Specific and Goal-Oriented Tasks ». Robotics 9, n^o 2 (7 mai 2020) : 31. http://dx.doi.org/10.3390/robotics9020031.

Texte intégral

Résumé :

Developing dialogue services for robots has been promoted nowadays for providing natural human–robot interactions to enhance user experiences. In this study, we adopted a service-oriented framework to develop emotion-aware dialogues for service robots. Considering the importance of the contexts and contents of dialogues in delivering robot services, our framework employed deep learning methods to develop emotion classifiers and two types of dialogue models of dialogue services. In the first type of dialogue service, the robot works as a consultant, able to provide domain-specific knowledge to users. We trained different neural models for mapping questions and answering sentences, tracking the human emotion during the human–robot dialogue, and using the emotion information to decide the responses. In the second type of dialogue service, the robot continuously asks the user questions related to a task with a specific goal, tracks the user’s intention through the interactions and provides suggestions accordingly. A series of experiments and performance comparisons were conducted to evaluate the major components of the presented framework and the results showed the promise of our approach.

Styles APA, Harvard, Vancouver, ISO, etc.

30

Mu, Yan Hua. « Task-Oriented Architecture for a Humanoid Robot ». Applied Mechanics and Materials 40-41 (novembre 2010) : 228–34. http://dx.doi.org/10.4028/www.scientific.net/amm.40-41.228.

Texte intégral

Résumé :

A humanoid robot is developed to perform various kinds of tasks in human daily environments. In this paper, three advanced capabilities which are indispensable for a humanoid robot to perform tasks, namely, natural human-humanoid robot interaction based on spoken dialogue and vision, vision-based navigation in complex and dynamic environments, object grasp and manipulation with hand-eye coordination, are discussed firstly. Then, a biologically-inspired system structure for a humanoid robot is presented. Based on this system structure, a task-oriented layered architecture for a humanoid robot is proposed, and the architectures of the three advanced capabilities are presented, respectively.

Styles APA, Harvard, Vancouver, ISO, etc.

31

MATSUI, Tatsuya, et Masafumi HAGIWARA. « Non-task-oriented Dialogue System with Humor Considering Utterances Polarity ». Transactions of Japan Society of Kansei Engineering 14, n^o 1 (2015) : 9–16. http://dx.doi.org/10.5057/jjske.14.9.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

32

Green, Nancy, et Jill Fain Lehman. « An Integrated Discourse Recipe-Based Model for Task-Oriented Dialogue ». Discourse Processes 33, n^o 2 (mars 2002) : 133–58. http://dx.doi.org/10.1207/s15326950dp3302_02.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

33

Poncin, Kristina, et Hannes Rieser. « Multi-speaker utterances and co-ordination in task-oriented dialogue ». Journal of Pragmatics 38, n^o 5 (mai 2006) : 718–44. http://dx.doi.org/10.1016/j.pragma.2005.06.013.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

34

Rastogi, Abhinav, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta et Pranav Khaitan. « Towards Scalable Multi-Domain Conversational Agents : The Schema-Guided Dialogue Dataset ». Proceedings of the AAAI Conference on Artificial Intelligence 34, n^o 05 (3 avril 2020) : 8689–96. http://dx.doi.org/10.1609/aaai.v34i05.6394.

Texte intégral

Résumé :

Virtual assistants such as Google Assistant, Alexa and Siri provide a conversational interface to a large number of services and APIs spanning multiple domains. Such systems need to support an ever-increasing number of services with possibly overlapping functionality. Furthermore, some of these services have little to no training data available. Existing public datasets for task-oriented dialogue do not sufficiently capture these challenges since they cover few domains and assume a single static ontology per domain. In this work, we introduce the the Schema-Guided Dialogue (SGD) dataset, containing over 16k multi-domain conversations spanning 16 domains. Our dataset exceeds the existing task-oriented dialogue corpora in scale, while also highlighting the challenges associated with building large-scale virtual assistants. It provides a challenging testbed for a number of tasks including language understanding, slot filling, dialogue state tracking and response generation. Along the same lines, we present a schema-guided paradigm for task-oriented dialogue, in which predictions are made over a dynamic set of intents and slots, provided as input, using their natural language descriptions. This allows a single dialogue system to easily support a large number of services and facilitates simple integration of new services without requiring additional training data. Building upon the proposed paradigm, we release a model for dialogue state tracking capable of zero-shot generalization to new APIs, while remaining competitive in the regular setting.

Styles APA, Harvard, Vancouver, ISO, etc.

35

Firdaus, Mauajama, Nidhi Thakur et Asif Ekbal. « Aspect-Aware Response Generation for Multimodal Dialogue System ». ACM Transactions on Intelligent Systems and Technology 12, n^o 2 (mars 2021) : 1–33. http://dx.doi.org/10.1145/3430752.

Texte intégral

Résumé :

Multimodality in dialogue systems has opened up new frontiers for the creation of robust conversational agents. Any multimodal system aims at bridging the gap between language and vision by leveraging diverse and often complementary information from image, audio, and video, as well as text. For every task-oriented dialog system, different aspects of the product or service are crucial for satisfying the user’s demands. Based upon the aspect, the user decides upon selecting the product or service. The ability to generate responses with the specified aspects in a goal-oriented dialogue setup facilitates user satisfaction by fulfilling the user’s goals. Therefore, in our current work, we propose the task of aspect controlled response generation in a multimodal task-oriented dialog system. We employ a multimodal hierarchical memory network for generating responses that utilize information from both text and images. As there was no readily available data for building such multimodal systems, we create a Multi-Domain Multi-Modal Dialog (MDMMD++) dataset. The dataset comprises the conversations having both text and images belonging to the four different domains, such as hotels, restaurants, electronics, and furniture. Quantitative and qualitative analysis on the newly created MDMMD++ dataset shows that the proposed methodology outperforms the baseline models for the proposed task of aspect controlled response generation.

Styles APA, Harvard, Vancouver, ISO, etc.

36

Park, Jeiyoon, Chanhee Lee, Chanjun Park, Kuekyeng Kim et Heuiseok Lim. « Variational Reward Estimator Bottleneck : Towards Robust Reward Estimator for Multidomain Task-Oriented Dialogue ». Applied Sciences 11, n^o 14 (19 juillet 2021) : 6624. http://dx.doi.org/10.3390/app11146624.

Texte intégral

Résumé :

Despite its significant effectiveness in adversarial training approaches to multidomain task-oriented dialogue systems, adversarial inverse reinforcement learning of the dialogue policy frequently fails to balance the performance of the reward estimator and policy generator. During the optimization process, the reward estimator frequently overwhelms the policy generator, resulting in excessively uninformative gradients. We propose the variational reward estimator bottleneck (VRB), which is a novel and effective regularization strategy that aims to constrain unproductive information flows between inputs and the reward estimator. The VRB focuses on capturing discriminative features by exploiting information bottleneck on mutual information. Quantitative analysis on a multidomain task-oriented dialogue dataset demonstrates that the VRB significantly outperforms previous studies.

Styles APA, Harvard, Vancouver, ISO, etc.

37

Kim, June-Woo, Hyekyung Yoon et Ho-Young Jung. « Improved Spoken Language Representation for Intent Understanding in a Task-Oriented Dialogue System ». Sensors 22, n^o 4 (15 février 2022) : 1509. http://dx.doi.org/10.3390/s22041509.

Texte intégral

Résumé :

Successful applications of deep learning technologies in the natural language processing domain have improved text-based intent classifications. However, in practical spoken dialogue applications, the users’ articulation styles and background noises cause automatic speech recognition (ASR) errors, and these may lead language models to misclassify users’ intents. To overcome the limited performance of the intent classification task in the spoken dialogue system, we propose a novel approach that jointly uses both recognized text obtained by the ASR model and a given labeled text. In the evaluation phase, only the fine-tuned recognized language model (RLM) is used. The experimental results show that the proposed scheme is effective at classifying intents in the spoken dialogue system containing ASR errors.

Styles APA, Harvard, Vancouver, ISO, etc.

38

Jordan, P. W., et M. A. Walker. « Learning Content Selection Rules for Generating Object Descriptions in Dialogue ». Journal of Artificial Intelligence Research 24 (1 juillet 2005) : 157–94. http://dx.doi.org/10.1613/jair.1591.

Texte intégral

Résumé :

A fundamental requirement of any task-oriented dialogue system is the ability to generate object descriptions that refer to objects in the task domain. The subproblem of content selection for object descriptions in task-oriented dialogue has been the focus of much previous work and a large number of models have been proposed. In this paper, we use the annotated COCONUT corpus of task-oriented design dialogues to develop feature sets based on Dale and Reiter's (1995) incremental model, Brennan and Clark's (1996) conceptual pact model, and Jordan's (2000b) intentional influences model, and use these feature sets in a machine learning experiment to automatically learn a model of content selection for object descriptions. Since Dale and Reiter's model requires a representation of discourse structure, the corpus annotations are used to derive a representation based on Grosz and Sidner's (1986) theory of the intentional structure of discourse, as well as two very simple representations of discourse structure based purely on recency. We then apply the rule-induction program RIPPER to train and test the content selection component of an object description generator on a set of 393 object descriptions from the corpus. To our knowledge, this is the first reported experiment of a trainable content selection component for object description generation in dialogue. Three separate content selection models that are based on the three theoretical models, all independently achieve accuracies significantly above the majority class baseline (17%) on unseen test data, with the intentional influences model (42.4%) performing significantly better than either the incremental model (30.4%) or the conceptual pact model (28.9%). But the best performing models combine all the feature sets, achieving accuracies near 60%. Surprisingly, a simple recency-based representation of discourse structure does as well as one based on intentional structure. To our knowledge, this is also the first empirical comparison of a representation of Grosz and Sidner's model of discourse structure with a simpler model for any generation task.

Styles APA, Harvard, Vancouver, ISO, etc.

39

Huang, Xinting, Jianzhong Qi, Yu Sun et Rui Zhang. « MALA : Cross-Domain Dialogue Generation with Action Learning ». Proceedings of the AAAI Conference on Artificial Intelligence 34, n^o 05 (3 avril 2020) : 7977–84. http://dx.doi.org/10.1609/aaai.v34i05.6306.

Texte intégral

Résumé :

Response generation for task-oriented dialogues involves two basic components: dialogue planning and surface realization. These two components, however, have a discrepancy in their objectives, i.e., task completion and language quality. To deal with such discrepancy, conditioned response generation has been introduced where the generation process is factorized into action decision and language generation via explicit action representations. To obtain action representations, recent studies learn latent actions in an unsupervised manner based on the utterance lexical similarity. Such an action learning approach is prone to diversities of language surfaces, which may impinge task completion and language quality. To address this issue, we propose multi-stage adaptive latent action learning (MALA) that learns semantic latent actions by distinguishing the effects of utterances on dialogue progress. We model the utterance effect using the transition of dialogue states caused by the utterance and develop a semantic similarity measurement that estimates whether utterances have similar effects. For learning semantic actions on domains without dialogue states, MALA extends the semantic similarity measurement across domains progressively, i.e., from aligning shared actions to learning domain-specific actions. Experiments using multi-domain datasets, SMD and MultiWOZ, show that our proposed model achieves consistent improvements over the baselines models in terms of both task completion and language quality.

Styles APA, Harvard, Vancouver, ISO, etc.

40

Li, Yangming, et Kaisheng Yao. « Interpretable NLG for Task-oriented Dialogue Systems with Heterogeneous Rendering Machines ». Proceedings of the AAAI Conference on Artificial Intelligence 35, n^o 15 (18 mai 2021) : 13306–14. http://dx.doi.org/10.1609/aaai.v35i15.17571.

Texte intégral

Résumé :

End-to-end neural networks have achieved promising performances in natural language generation (NLG). However, they are treated as black boxes and lack interpretability. To address this problem, we propose a novel framework, heterogeneous rendering machines (HRM), that interprets how neural generators render an input dialogue act (DA) into an utterance. HRM consists of a renderer set and a mode switcher. The renderer set contains multiple decoders that vary in both structure and functionality. For every generation step, the mode switcher selects an appropriate decoder from the renderer set to generate an item (a word or a phrase). To verify the effectiveness of our method, we have conducted extensive experiments on 5 benchmark datasets. In terms of automatic metrics (e.g., BLEU), our model is competitive with the current state-of-the-art method. The qualitative analysis shows that our model can interpret the rendering process of neural generators well. Human evaluation also confirms the interpretability of our proposed approach.

Styles APA, Harvard, Vancouver, ISO, etc.

41

TOKUHISA, Ryoko, et Ryuta TERASHIMA. « An Analysis of 'Distinctive' Utterances in Non-task-oriented Conversational Dialogue ». Transactions of the Japanese Society for Artificial Intelligence 22 (2007) : 425–35. http://dx.doi.org/10.1527/tjsai.22.425.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

42

Kobyashi, Shunya, et Masafumi Hagiwara. « Non-task-oriented Dialogue System Considering User's Preference and Human Relations ». Transactions of the Japanese Society for Artificial Intelligence 31, n^o 1 (2016) : DSF—A_1–10. http://dx.doi.org/10.1527/tjsai.dsf-502.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

43

Sardinha, Tony Berber. « Building Coherence and Cohesion : Task-oriented Dialogue in English and Spanish ». Computational Linguistics 32, n^o 2 (juin 2006) : 287–89. http://dx.doi.org/10.1162/coli.2006.32.2.287.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

44

Liu, Zihan, Genta Indra Winata, Zhaojiang Lin, Peng Xu et Pascale Fung. « Attention-Informed Mixed-Language Training for Zero-Shot Cross-Lingual Task-Oriented Dialogue Systems ». Proceedings of the AAAI Conference on Artificial Intelligence 34, n^o 05 (3 avril 2020) : 8433–40. http://dx.doi.org/10.1609/aaai.v34i05.6362.

Texte intégral

Résumé :

Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of high-quality data. In order to circumvent the expensive and time-consuming data collection, we introduce Attention-Informed Mixed-Language Training (MLT), a novel zero-shot adaptation method for cross-lingual task-oriented dialogue systems. It leverages very few task-related parallel word pairs to generate code-switching sentences for learning the inter-lingual semantics across languages. Instead of manually selecting the word pairs, we propose to extract source words based on the scores computed by the attention layer of a trained English task-related model and then generate word pairs using existing bilingual dictionaries. Furthermore, intensive experiments with different cross-lingual embeddings demonstrate the effectiveness of our approach. Finally, with very few word pairs, our model achieves significant zero-shot adaptation performance improvements in both cross-lingual dialogue state tracking and natural language understanding (i.e., intent detection and slot filling) tasks compared to the current state-of-the-art approaches, which utilize a much larger amount of bilingual data.

Styles APA, Harvard, Vancouver, ISO, etc.

45

Zhou, Yangyang, et Fuji Ren. « CERG : Chinese Emotional Response Generator with Retrieval Method ». Research 2020 (7 septembre 2020) : 1–8. http://dx.doi.org/10.34133/2020/2616410.

Texte intégral

Résumé :

The dialogue system has always been one of the important topics in the domain of artificial intelligence. So far, most of the mature dialogue systems are task-oriented based, while non-task-oriented dialogue systems still have a lot of room for improvement. We propose a data-driven non-task-oriented dialogue generator “CERG” based on neural networks. This model has the emotion recognition capability and can generate corresponding responses. The data set we adopt comes from the NTCIR-14 STC-3 CECG subtask, which contains more than 1.7 million Chinese Weibo post-response pairs and 6 emotion categories. We try to concatenate the post and the response with the emotion, then mask the response part of the input text character by character to emulate the encoder-decoder framework. We use the improved transformer blocks as the core to build the model and add regularization methods to alleviate the problems of overcorrection and exposure bias. We introduce the retrieval method to the inference process to improve the semantic relevance of generated responses. The results of the manual evaluation show that our proposed model can make different responses to different emotions to improve the human-computer interaction experience. This model can be applied to lots of domains, such as automatic reply robots of social application.

Styles APA, Harvard, Vancouver, ISO, etc.

46

Li, Kuo-Chen, Maiga Chang et Kuan-Hsing Wu. « Developing a Task-Based Dialogue System for English Language Learning ». Education Sciences 10, n^o 11 (28 octobre 2020) : 306. http://dx.doi.org/10.3390/educsci10110306.

Texte intégral

Résumé :

This research involved the design of a task-based dialogue system and evaluation of its learning effectiveness. Dialogue training still heavily depends on human communication with instant feedback or correction. However, it is not possible to provide a personal tutor for every English learner. With the rapid development of information technology, digitized learning and voice communication is a possible solution. The goal of this research was to develop an innovative model to refine the task-based dialogue system, including natural language understanding, disassembly intention, and dialogue state tracking. To enable the dialogue system to find the corresponding sentence accurately, the dialogue system was designed with machine learning algorithms to allow users to communicate in a task-based fashion. Past research has pointed out that computer-assisted instruction has achieved remarkable results in language reading, writing, and listening. Therefore, the direction of the discussion is to use the task-oriented dialogue system as a speaking teaching assistant. To train the speaking ability, the proposed system provides a simulation environment with goal-oriented characteristics, allowing learners to continuously improve their language fluency in terms of speaking ability by simulating conversational situational exercises. To evaluate the possibility of replacing the traditional English speaking practice with the proposed system, a small English speaking class experiment was carried out to validate the effectiveness of the proposed system. Data of 28 students with three assigned tasks were collected and analyzed. The promising results of the collected students’ feedback confirm the positive perceptions toward the system regarding user interface, learning style, and the system’s effectiveness.

Styles APA, Harvard, Vancouver, ISO, etc.

47

Firdaus, Mauajama, Arunav Pratap Shandeelya et Asif Ekbal. « More to diverse : Generating diversified responses in a task oriented multimodal dialog system ». PLOS ONE 15, n^o 11 (5 novembre 2020) : e0241271. http://dx.doi.org/10.1371/journal.pone.0241271.

Texte intégral

Résumé :

Multimodal dialogue system, due to its many-fold applications, has gained much attention to the researchers and developers in recent times. With the release of large-scale multimodal dialog dataset Saha et al. 2018 on the fashion domain, it has been possible to investigate the dialogue systems having both textual and visual modalities. Response generation is an essential aspect of every dialogue system, and making the responses diverse is an important problem. For any goal-oriented conversational agent, the system’s responses must be informative, diverse and polite, that may lead to better user experiences. In this paper, we propose an end-to-end neural framework for generating varied responses in a multimodal dialogue setup capturing information from both the text and image. Multimodal encoder with co-attention between the text and image is used for focusing on the different modalities to obtain better contextual information. For effective information sharing across the modalities, we combine the information of text and images using the BLOCK fusion technique that helps in learning an improved multimodal representation. We employ stochastic beam search with Gumble Top K-tricks to achieve diversified responses while preserving the content and politeness in the responses. Experimental results show that our proposed approach performs significantly better compared to the existing and baseline methods in terms of distinct metrics, and thereby generates more diverse responses that are informative, interesting and polite without any loss of information. Empirical evaluation also reveals that images, while used along with the text, improve the efficiency of the model in generating diversified responses.

Styles APA, Harvard, Vancouver, ISO, etc.

48

Hassan, Javeria, Muhammad Ali Tahir et Adnan Ali. « Natural language understanding of map navigation queries in Roman Urdu by joint entity and intent determination ». PeerJ Computer Science 7 (21 juillet 2021) : e615. http://dx.doi.org/10.7717/peerj-cs.615.

Texte intégral

Résumé :

Navigation based task-oriented dialogue systems provide users with a natural way of communicating with maps and navigation software. Natural language understanding (NLU) is the first step for a task-oriented dialogue system. It extracts the important entities (slot tagging) from the user’s utterance and determines the user’s objective (intent determination). Word embeddings are the distributed representations of the input sentence, and encompass the sentence’s semantic and syntactic representations. We created the word embeddings using different methods like FastText, ELMO, BERT and XLNET; and studied their effect on the natural language understanding output. Experiments are performed on the Roman Urdu navigation utterances dataset. The results show that for the intent determination task XLNET based word embeddings outperform other methods; while for the task of slot tagging FastText and XLNET based word embeddings have much better accuracy in comparison to other approaches.

Styles APA, Harvard, Vancouver, ISO, etc.

49

Choi, Sung-Kwon, Yo-Han Lee et Oh-Wook Kwon. « A study on task-oriented dialogue data of a dialogue system for foreign language tutoring : Focusing on Korean dialogue data. » Foreign Languages Education 29, n^o 1 (28 février 2022) : 105–24. http://dx.doi.org/10.15334/fle.2022.29.1.105.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

50

Sun, Yajing, Yong Shan, Chengguang Tang, Yue Hu, Yinpei Dai, Jing Yu, Jian Sun, Fei Huang et Luo Si. « Unsupervised Learning of Deterministic Dialogue Structure with Edge-Enhanced Graph Auto-Encoder ». Proceedings of the AAAI Conference on Artificial Intelligence 35, n^o 15 (18 mai 2021) : 13869–77. http://dx.doi.org/10.1609/aaai.v35i15.17634.

Texte intégral

Résumé :

It is important for task-oriented dialogue systems to discover the dialogue structure (i.e. the general dialogue flow) from dialogue corpora automatically. Previous work models dialogue structure by extracting latent states for each utterance first and then calculating the transition probabilities among states. These two-stage methods ignore the contextual information when calculating the probabilities, which makes the transitions between the states ambiguous. This paper proposes a conversational graph (CG) to represent deterministic dialogue structure where nodes and edges represent the utterance and context information respectively. An unsupervised Edge-Enhanced Graph Auto-Encoder (EGAE) architecture is designed to model local-contextual and global-structural information for conversational graph learning. Furthermore, a self-supervised objective is introduced with the response selection task to guide the unsupervised learning of the dialogue structure. Experimental results on several public datasets demonstrate that the novel model outperforms several alternatives in aggregating utterances with similar semantics. The effectiveness of the learned dialogue structured is also verified by more than 5\% joint accuracy improvement in the downstream task of low resource dialogue state tracking.

Styles APA, Harvard, Vancouver, ISO, etc.

Articles de revues sur le sujet « Task-oriented dialogue »

Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres