Filters








10,703 Hits in 3.8 sec

Knowledge transfer between speakers for personalised dialogue management

Iñigo Casanueva, Thomas Hain, Heidi Christensen, Ricard Marxer, Phil Green
2015 Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue  
Recently, Gaussian process based reinforcement learning methods have been shown to reduce the number of dialogues needed to reach optimal performance, and pre-training the policy with data gathered from  ...  Model-free reinforcement learning has been shown to be a promising data driven approach for automatic dialogue policy optimization, but a relatively large amount of dialogue interactions is needed before  ...  The authors would like to thank David Martínez for providing the i-vectors used in this paper.  ... 
doi:10.18653/v1/w15-4603 dblp:conf/sigdial/CasanuevaHCMG15 fatcat:6mmekrqmkbfh7e7ko7uwcqfwnm

Domain Complexity and Policy Learning in Task-Oriented Dialogue Systems [chapter]

Alexandros Papangelis, Stefan Ultes, Yannis Stylianou
2018 Lecture Notes in Electrical Engineering  
In the present paper, we conduct a comparative evaluation of a multitude of information-seeking domains, using two well-known but fundamentally different algorithms for policy learning: GP-SARSA and DQN  ...  Our results indicate several main domain characteristics that play an important role in policy learning performance in terms of task success rates.  ...  Using statistical methods for dialogue policy learning (and consequently dialogue management) has prevailed in the state of the art for many years.  ... 
doi:10.1007/978-3-319-92108-2_8 fatcat:kpgqwlsum5hulibunx3ioputri

An End-to-End Conversational Second Screen Application for TV Program Discovery

Peter Z. Yeh, Deepak Ramachandran, Benjamin Douglas, Adwait Ratnaparkhi, William Jarrold, Ronald Provine, Peter F. Patel-Schneider, Stephen Laverty, Nirvana Tikku, Sean Brown, Jeremy Mendel, Adam Emfield
2015 The AI Magazine  
In this article, we report on a multiphase R&D effort to develop a conversational second screen application for TV program discovery.  ...  Our goal is to share with the community the breadth of artificial intelligence (AI) and natural language (NL) technologies required to develop such an application along with learnings from target end-users  ...  Kaplan for his encouragement, guidance, and support on this project. The authors would also like to thank the reviewers for their helpful feedback and suggestions for improving the article. Notes  ... 
doi:10.1609/aimag.v36i3.2604 fatcat:kovzpzhslnaudgvn4tbyb65d6e

A Spoken Dialogue System for Electronic Program Guide Information Access

Seokhwan Kim, Cheongjae Lee, Sangkeun Jung, Gary Geunbae Lee
2007 RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication  
database based on automatically extracted information from popular EPG websites.  ...  In this paper, we present POSTECH Spoken Dialogue System for Electronic Program Guide Information Access (POSSDS-EPG).  ...  by the Invitation for Proposals on Internet Services Theme funded by Microsoft Research Asia.  ... 
doi:10.1109/roman.2007.4415076 dblp:conf/ro-man/KimLJL07 fatcat:og7tvugnc5aldlyy2qkhzwwxn4

Improving Generalisation to New Speakers in Spoken Dialogue State Tracking

Iñigo Casanueva, Thomas Hain, Phil Green
2016 Interspeech 2016  
Statistical dialogue management has shown resilience against high ASR error rates, hence making it useful to improve the performance of these interfaces.  ...  However, little research was devoted to dialogue management personalisation to specific users so far.  ...  The authors would like to thank David Martínez for providing the iVectors used in this paper.  ... 
doi:10.21437/interspeech.2016-404 dblp:conf/interspeech/CasanuevaHG16 fatcat:e44dmbgb5ng4rburjfaygvhk2q

DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization

Ming Zhong, Yang Liu, Yichong Xu, Chenguang Zhu, Michael Zeng
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
For a dialogue, it corrupts a window of text with dialogue-inspired noise, and guides the model to reconstruct this window based on the content of the remaining conversation.  ...  Considering the nature of long conversations, we propose a window-based denoising approach for generative pre-training.  ...  Acknowledgements We thank Shaohan Huang for providing guidance on pretraining UniLM-CP.  ... 
doi:10.1609/aaai.v36i10.21432 fatcat:w66ewazmujb33bsi3g4cpn2zzm

Challenges of Building an Intelligent Chatbot

Anna Chizhik, Yulia Zherebtsova
2020 International Conference "Internet and Modern Society"  
The retrieval-based model, which achieved the best dialogue performance, is proposed. Furthermore, we present the datasets collected for the purpose of this paper.  ...  However, building an intelligent chatbot is challenging as it requires spoken language understanding, dialogue context awareness and human-like aspects demonstration.  ...  One of the most basic vectorization methods is the statistical measure TF-IDF [22] , it determines the word importance to the document in a text collection.  ... 
dblp:conf/ims2/ChizhikZ20 fatcat:tptdmej6rrd4hp3s4rf2qsdcmq

SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues [article]

Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu, Song-Chun Zhu
2022 arXiv   pre-print
Inferring social relations from dialogues is vital for building emotionally intelligent robots to interpret human language better and act accordingly.  ...  attributes and relations conditioned on the semantics of dialogues, (ii) a β process updating the social relations based on related attributes, and (iii) a γ process updating individual's attributes based  ...  We would like to thank Yaofang Zhang and Qian Long for valuable discussions. We also thank the outstanding reviewers for their helpful comments to improve our manuscript.  ... 
arXiv:2106.01006v3 fatcat:fo5k7bbx6rcydfghlpkvbpsh54

Data-Driven Dialogue Systems for Social Agents [chapter]

Kevin K. Bowden, Shereen Oraby, Amita Misra, Jiaqi Wu, Stephanie Lukin, Marilyn Walker
2018 Lecture Notes in Electrical Engineering  
We also examine methods for transfer learning between datasets and the use of external knowledge. Finally, we discuss appropriate choices of evaluation metrics for the learning objective.  ...  To facilitate research in this area, we have carried out a wide survey of publicly available datasets suitable for data-driven learning of dialogue systems.  ...  The authors also thank Nissan Pow, Michael Noseworthy, Chia-Wei Liu, Gabriel Forgues, Alessandro Sordoni, Yoshua Bengio and Aaron Courville for helpful discussions.  ... 
doi:10.1007/978-3-319-92108-2_6 fatcat:nrqzpujukreojdkkusbzy4uniy

A Neural Network Approach to Intention Modeling for User-Adapted Conversational Agents

David Griol, Zoraida Callejas
2016 Computational Intelligence and Neuroscience  
In this contribution, we present a framework based on neural networks that allows modeling of the user's intention during the dialogue and uses this prediction to dynamically adapt the dialogue model of  ...  Spoken dialogue systems have been proposed to enable a more natural and intuitive interaction with the environment and human-computer interfaces.  ...  The statistical methodology that we propose for dialogue management is based on using a data corpus to learn the next system action considering the history of the dialogue up to the current moment and  ... 
doi:10.1155/2016/8402127 pmid:26819592 pmcid:PMC4706878 fatcat:qpypf2vut5eynbi6spgovpa5ni

Using phone features to improve dialogue state tracking generalisation to unseen states

Iñigo Casanueva, Thomas Hain, Mauro Nicolao, Phil Green
2016 Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue  
In a slot-based dialogue system, dialogue states lie in discrete space where distances between states cannot be computed.  ...  Therefore, the model parameters to track states unseen in the training data can only be estimated from more general statistics, under the assumption that every dialogue state will have the same underlying  ...  Dialogue corpus One of the main problems in dialogue management research is the lack of annotated dialogue corpora. The corpora released for the first three DSTCs aimed to mitigate this problem.  ... 
doi:10.18653/v1/w16-3611 dblp:conf/sigdial/CasanuevaHNG16 fatcat:ki3eqhxb4zhp5czyt42qethtta

Design for an Interactive Television Advertising System

Jong Woo Kim, Stephen Du
2006 Proceedings of the 39th Annual Hawaii International Conference on System Sciences (HICSS'06)  
Most information systems research in the interactive television domain focuses on improving methods for choosing program content.  ...  A proof-of-concept prototype based on this design was implemented and validated in a pilot test. Implications for the advertising industry and for future research are discussed.  ...  Based on that data, the dialogue engine selects agents and dialogue scripts targeted for specific viewers. Then this component inserts agent and script with voice at the end of AD.  ... 
doi:10.1109/hicss.2006.116 dblp:conf/hicss/KimD06 fatcat:axadqh5ypncgzhm2fiwtiefu4i

2003 AAAI Spring Symposium Series

Andreas Abecker, Erik K. Antonsson, Charles B. Callaway, Virginia Dignum, Patrick Doherty, Ludger van Elst, Michael Freed, Reva Freedman, Hans W. Guesgen, Gareth J. F. Jones, John R. Koza, David Kortenkamp (+6 others)
2003 The AI Magazine  
, turn taking and dialogue management, corpus-based dialogue generation, analogy generation for intelligent tutoring systems, and generation of specific linguistic phenomena such as clarification questions  ...  in knowledge management-supporting and extending human interaction and learning-and, therefore, a need for intelligence-enhanced, integrated, and personalized solutions.  ...  intelligence.  ... 
doi:10.1609/aimag.v24i3.1723 dblp:journals/aim/AbeckerACDDEFFGJKKMMMRSW03 fatcat:b7s542czdfdlnbjlvaxhxgb7dy

Discussion on Fruiter Professional Information Service Mode of Shandong Province [chapter]

Wang Zhi-jun, Jiang Meng, Cheng Shu-han
2014 IFIP Advances in Information and Communication Technology  
integration, information service mode, the construction of base and information site, building of expert team and training system are discussed in this paper.  ...  The research results have theoretical significance and practical value on the construction of rural informatization demonstration province.  ...  Based on the above, a variety of agricultural "computer expert" computer software system with intelligent analysis and reasoning, independent knowledge base which is very convenient to increase and modify  ... 
doi:10.1007/978-3-642-54344-9_19 fatcat:5d3utvu6wvgwfop4thwvw4ooai

Interactive Pattern Recognition and Human Language Technology for Digital Audiovisual Content Processing

Antonio L. Lagarda, Jorge Civera, Alfons Juan, Francisco Casacuberta
2010 Journal of machine learning research  
tool to encapsulate, distribute and intelligently use digital content such as that showed on thematic TV channels.  ...  involve 19 research groups, including PRHLT. i3media focuses on the creation and automated management of intelligent audiovisual content, so as to facilitate both, content personalisation and interaction  ...  Once captions are made available, the user can search for audiovisual content based on keywords.  ... 
dblp:journals/jmlr/LagardaCJC10 fatcat:a5gmbwxvkvhc3iyngc6bhosneq
« Previous Showing results 1 — 15 out of 10,703 results