Filters








9,609 Hits in 5.2 sec

Crowd-Sourced Collection of Task-Oriented Human-Human Dialogues in a Multi-domain Scenario [chapter]

Norbert Braunschweiler, Panagiotis Papadakos, Margarita Kotti, Yannis Marketakis, Yannis Tzitzikas
2019 Lecture Notes in Computer Science  
This paper describes a dialogue collection process which used crowd-sourcing and a Wizard-of-Oz set-up to collect written human-human dialogues for a task-oriented, multi-domain scenario.  ...  There is a lack of high-quality corpora for the purposes of training task-oriented, end-to-end dialogue systems.  ...  [6, 11, 12] ) lack a grounding of the dialogues onto a knowledge base which limits their use for task-oriented systems.  ... 
doi:10.1007/978-3-030-27947-9_34 fatcat:z277rreqprexjggcgxt3pnkqoq

Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access [article]

Seokhwan Kim, Mihail Eric, Karthik Gopalakrishnan, Behnam Hedayatnia, Yang Liu, Dilek Hakkani-Tur
2020 arXiv   pre-print
In this paper, we propose to expand coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.  ...  We define three sub-tasks: knowledge-seeking turn detection, knowledge selection, and knowledge-grounded response generation, which can be modeled individually or jointly.  ...  Figure 1 :Figure 2 : 12 Examples of task-oriented conversations with unstructured knowledge access Dialogue Context ( " A baseline architecture for task-oriented conversational modeling grounded on unstructured  ... 
arXiv:2006.03533v1 fatcat:ye5lha24azhcdoyzjsprrzdbom

LD-SDS: Towards an Expressive Spoken Dialogue System based on Linked-Data [article]

Alexandros Papangelis, Panagiotis Papadakos, Margarita Kotti, Yannis Stylianou, Yannis Tzitzikas, Dimitris Plexousakis
2017 arXiv   pre-print
Specifically, we focus on: a) improving the identification, disambiguation and linking of entities occurring in data sources and user input; b) offering advanced query services for exploiting the semantics  ...  In this work we discuss the related challenges and describe an approach towards the fusion of state-of-the-art technologies from the Spoken Dialogue Systems (SDS) and the Semantic Web and Information Retrieval  ...  Recently, efforts are being made towards multi-domain SDS, as well as SDS that work with large knowledge graphs that combine independent domain-specific databases with other knowledge bases (e.g.  ... 
arXiv:1710.02973v1 fatcat:4wwpub2bkjatbhwh7kjafhyp5i

Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation [article]

Yu Li, Baolin Peng, Yelong Shen, Yi Mao, Lars Liden, Zhou Yu, Jianfeng Gao
2021 arXiv   pre-print
To address these challenges, we present PLUG, a language model that homogenizes different knowledge sources to a unified knowledge representation for knowledge-grounded dialogue generation tasks.  ...  It can generalize to different downstream knowledge-grounded dialogue generation tasks with a few training examples.  ...  In Proceedings of the 2021 Conference on language model for task-oriented dialogue.  ... 
arXiv:2112.07924v1 fatcat:aw6sd4ilu5fjbfagtc42g74dhe

User Modeling for Task Oriented Dialogues [article]

Izzeddin Gur, Dilek Hakkani-Tur, Gokhan Tur, Pararth Shah
2018 arXiv   pre-print
We introduce end-to-end neural network based models for simulating users of task-oriented dialogue systems.  ...  User simulation in dialogue systems is crucial from two different perspectives: (i) automatic evaluation of different dialogue models, and (ii) training task-oriented dialogue systems.  ...  simulated dialogues enriched with crowd realizations.  ... 
arXiv:1811.04369v1 fatcat:ky2ogstia5a5nlgtfvnswwb5he

Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems [article]

Anish Acharya, Suranjit Adhikari, Sanchit Agarwal, Vincent Auvray, Nehal Belgamwar, Arijit Biswas, Shubhra Chandra, Tagyoung Chung, Maryam Fazel-Zarandi, Raefer Gabriel, Shuyang Gao, Rahul Goel (+19 others)
2021 arXiv   pre-print
Traditional goal-oriented dialogue systems rely on various components such as natural language understanding, dialogue state tracking, policy learning and response generation.  ...  To overcome these problems, in this demo, we present Alexa Conversations, a new approach for building goal-oriented dialogue systems that is scalable, extensible as well as data efficient.  ...  End-to-end optimiza- tion of task-oriented dialogue model with deep rein- forcement learning. arXiv:1711.10712. X. Ma and E. Hovy. 2016.  ... 
arXiv:2104.09088v1 fatcat:djuah754a5h5he7vrtong3keji

Toward a new generation of virtual humans for interactive experiences

J. Rickel, S. Marsella, J. Gratch, R. Hill, D. Traum, W. Swartout
2002 IEEE Intelligent Systems  
Task-oriented dialogue Spoken dialogue is crucial for collaboration. Students must be able to ask their virtual human instructors a wide range of questions.  ...  aspects of the social context 6,7 and is oriented toward multiple participants and face-to-face communication 8 • A dialogue manager that recognizes dialogue acts from utterances, updates the dialogue  ... 
doi:10.1109/mis.2002.1024750 fatcat:u32d5u4f3bbqhk7ocu6vdlpqlq

A Context-Aware Conversational Agent in the Rehabilitation Domain

Thanassis Mavropoulos, Georgios Meditskos, Spyridon Symeonidis, Eleni Kamateri, Maria Rousi, Dimitris Tzimikas, Lefteris Papageorgiou, Christos Eleftheriadis, George Adamopoulos, Stefanos Vrochidis, Ioannis Kompatsiaris
2019 Future Internet  
The proposed approach capitalises on latest breakthroughs in computer vision, sensor management, speech recognition, natural language processing, knowledge representation, dialogue management, semantic  ...  In this paper, we present the underlying technologies and the theoretical background behind a health-care platform dedicated to supporting medical stuff and individuals with movement disabilities and to  ...  Discourse analysis results are then handled by the dialogue manager, which is also responsible for other tasks, like manipulating knowledge database queries, using previous analyses and dialogue history  ... 
doi:10.3390/fi11110231 fatcat:bzvt7rmb5bem5oipya7mrh6p6e

Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding [article]

Nouha Dziri, Andrea Madotto, Osmar Zaiane, Avishek Joey Bose
2021 arXiv   pre-print
In this paper, we focus on the task of improving the faithfulness -- and thus reduce hallucination -- of Neural Dialogue Systems to known facts supplied by a Knowledge Graph (KG).  ...  Our proposed model can easily be applied to any dialogue generated responses without retraining the model.  ...  Acknowledgements We are grateful to the anonymous reviewers for helpful comments.  ... 
arXiv:2104.08455v2 fatcat:pwq4iser2jbqdczqgtuhwdm3zm

Human Computations in Citizen Crowds: A Knowledge Management Solution Framework

Nadeem Kafi, Zubair Ahmed Shaikh Shaikh, Muhammad Shahid Shaikh
2018 Mehran University Research Journal of Engineering and Technology  
Literature shows little work on KM frameworks for citizen crowds, which gather input from the diverse category of Humans, organize that knowledge concerning tasks and knowledge categories and recreate  ...  KE (Knowledge Engineering) and KM (Knowledge Management) have tried to augment human knowledge on two separate planes: the first deals with machine interpretation of knowledge while the later explore interactions  ...  Muhammad Nauman Durrani, for participating in various discussions on different aspect of this paper, and students for their help while prototyping the web application.  ... 
doi:10.22581/muet1982.1803.06 fatcat:25w52kkwrreevpycbxvyqtmmgi

Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment

Siqi Bao, Huang He, Fan Wang, Rongzhong Lian, Hua Wu
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Under the deployed strategy, knowledge grounded conversations are conducted with two dialogue agents.  ...  For the sake of rational knowledge utilization and coherent conversation flow, a dialogue strategy which controls knowledge selection is instantiated and continuously adapted via reinforcement learning  ...  Acknowledgments We would like to thank the ACL reviewers for their constructive suggestions and Jinhua Peng, Chaotao Chen, Min Xie for the helpful discussions.  ... 
doi:10.18653/v1/p19-1535 dblp:conf/acl/BaoHWLW19 fatcat:auosmpzljfgefmvynz4g6wta5e

Neural Approaches to Conversational AI [article]

Jianfeng Gao, Michel Galley, Lihong Li
2019 arXiv   pre-print
We group conversational systems into three categories: (1) question answering agents, (2) task-oriented dialogue agents, and (3) chatbots.  ...  For each category, we present a review of state-of-the-art neural approaches, draw the connection between them and traditional approaches, and discuss the progress that has been made and challenges still  ...  useful for task-oriented dialogues as well.  ... 
arXiv:1809.08267v3 fatcat:j57xlm4ogferdnrpfs4f2jporq

A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis [article]

Jiawei Liu, Kaisong Song, Yangyang Kang, Guoxiu He, Zhuoren Jiang, Changlong Sun, Wei Lu, Xiaozhong Liu
2021 arXiv   pre-print
In this study, we propose a novel model, Role-Selected Sharing Network (RSSN), which integrates both dialogue satisfaction estimation and handoff prediction in one multi-task learning framework.  ...  Specifically, we decouple the relation and interaction between the two tasks by the role information after the shared encoder.  ...  Acknowledgments We thank the anonymous reviewers for their valuable comments and suggestions.  ... 
arXiv:2109.08412v1 fatcat:ychg4cf4vnb6vezicbun2hiaiq

Towards Ontological Cognitive System [chapter]

Carles Fernandez, Jordi Gonzàlez, João Manuel R. S. Tavares, F. Xavier Roca
2013 Lecture Notes in Computational Vision and Biomechanics  
Future directions suggest to reinforce the multi-modal fusion of information sources and the communication with end-users.  ...  This raises a series of technological demands for automatic video understanding and management, which together with the compromising attentional limitations of human operators, have motivated the research  ...  (b) In some cases, a collaborative and integrative use of different knowledge sources allows us to achieve or enrich the accomplishment of these tasks.  ... 
doi:10.1007/978-94-007-0726-9_5 fatcat:kugu32atk5ahpcuppraqhhrsxi

Requirements elicitation: Towards the unknown unknowns

Alistair Sutcliffe, Pete Sawyer
2013 2013 21st IEEE International Requirements Engineering Conference (RE)  
Representations and models are also well established although there is potential for more sophisticated modelling of domain knowledge.  ...  A road map for future requirements elicitation research is proposed investigating the prospects for techniques, models and tools in green-field domains where few solutions exist, contrasted with brown-field  ...  Nevertheless, crowd sourcing and collaborative solutions combined with participatory design [82] may have potential for application to RE.  ... 
doi:10.1109/re.2013.6636709 dblp:conf/re/SutcliffeS13 fatcat:sjura3z4inbuxnanioqh6p5gza
« Previous Showing results 1 — 15 out of 9,609 results