Zum Inhalt springenZur Suche springen

Publikationen des Lehrstuhls Dialog Systems and Machine Learning

  • C. Geishauser, S. Hu, H.-C. Lin, N. Lubis, M. Heck, S. Feng, C. van Niekerk and M. Gašić, “What Does The User Want? Information Gain for Hierarchical Dialogue Policy Optimisation”, IEEE ASRU 2021 PDF

  • C. van Niekerk, A. Malinin, C. Geishauser, M. Heck, H-C. Lin, N. Lubis, S. Feng and M. Gašić, "Uncertainty Measures in Neural Belief Tracking: The Effects on Dialogue Policy Performance", EMNLP 2021 PDF

  • H-C. Lin, N. Lubis, S. Hu, C. van Niekerk, C. Geishauser, M. Heck, S. Feng and M. Gašić, „Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems”, SIGDIAL 2021 PDF

  • N. Lubis, C. Geishauser, M. Heck, H-C. Lin, M. Moresi, C. van Niekerk and M. Gašić, "LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization", COLING 2020 PDF
  • M. Heck, C. Geishauser, H-C. Lin, N. Lubis, M. Moresi, C. van Niekerk and M. Gašić, "Out-of-Task Training for Dialog State Tracking Models", COLING 2020 PDF
  • A. Jakubowski, M. Gašić, M. Zibrowius, "Topology of Word Embeddings: Singularities Reflect Polysemy", *SEM 2020 [Best Paper Award] PDF
  • Y.-C. Wu, B.-H. Tseng and M. Gašić, "Actor-Double-Critic: Incorporating Model-Based Critic for Task-Oriented Dialogue Systems", Findings of EMNLP 2020 PDF
  • C. van Niekerk, M. Heck, C. Geishauser, H-C. Lin, N. Lubis, M. Moresi and M. Gašić, "Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles", Findings of EMNLP 2020 PDF
  • M. Heck, C. van Niekerk, N. Lubis, C. Geishauser, H-C. Lin, M. Moresi and M. Gašić, "TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking", SIGDIAL, 2020 [Best Paper Award] PDF
  • N. Lubis, M. Heck, C. van Niekerk and M. Gašić, "Adaptable Conversational Machines", AI Magazine, 2020 Visit AI Magazine
  • B.-H. Tseng, P. Budzianowski, Y.-C. Wu and M. Gasic, "Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation", SIGDIAL, Stockholm, Sweden, 2019 PDF
  • L. Chen, Z. Chen, B. Tan, S. Long, M. Gasic and K. Yu, "AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning", IEEE TASLP, 2019 PDF
  • P. Wesselmann, Y.-C. Wu and M. Gašić, "Curiosity-driven Reinforcement Learning for Dialogue Management", ICASSP, Brighton, UK, 2019 PDF
  • L.M. Rojas-Barahona, B-H. Tseng, Y. Dai, C. Mansfield, O. Ramadan, S. Ultes, M. Crawford and M. Gašić, "Deep learning for language understanding of mental health concepts derived from Cognitive Behavioural Therapy", LOUHI, Brussels, Belgium, 2018 PDF
  • P. Budzianowski, T-H. Wen, B-H. Tseng, I. Casanueva, S. Ultes, O. Ramadan and M. Gašić, "MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling", EMNLP, Brussels, Belgium, 2018 [Best Resource Paper Award] PDF
  • O. Ramadan, P. Budzianowski and M. Gašić, "Large-scale Multi-Domain Belief Tracking with Knowledge Sharing", ACL, Melbourne, Australia, 2018 PDF
  • F. Kreyssig, I. Casanueva, P. Budzianowski and M. Gašić, "Neural User Simulation for Corpus-based Policy Optimisation of Spoken Dialogue Systems", Sigdial, Melbourne, Australia, 2018 PDF
  • B.-H. Tseng, F. Kreyssig, P. Budzianowski, I. Casanueva, Y.-C. Wu, S. Ultes and M. Gašić, "Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems", Sigdial, Melbourne, Australia, 2018 PDF
  • I. Casanueva, P. Budzianowski, F. Kreyssig, S. Ultes, B.-H. Tseng, Y.-C. Wu and M. Gašić, "Feudal Dialogue Management with Jointly Learned Feature Extractors", Sigdial, Melbourne, Australia, 2018 PDF
  • S. Ultes, P. Budzianowski, I. Casanueva, L.M. Rojas Barahona, B.-H. Tseng, Y.-C. Wu, S. Young and M. Gašić, "Addressing Objects and Their Relations: The Conversational Entity Dialogue Model", Sigdial, Melbourne, Australia, 2018 PDF
  • C. Tegho, P. Budzianowski and M. Gašić, "Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation", ICASSP, Calgary, Canada, 2018 [Best Student Paper Award] PDF
  • L. Chen, C. Chang, Z. Chen, B. Tan, M. Gašić and K. Yu, "Policy Adaptation for Deep Reinforcement Learning-based Dialogue Management", ICASSP, Calgary, Canada, 2018 PDF
  • I. Casanueva, P. Budzianowski, P-H. Su, S. Ultes, L.M. Rojas-Barahona, B.-H. Tseng and Milica Gašić, "Feudal Reinforcement Learning for Dialogue Management in Large Domains", NAACL, New Orleans, USA, 2018 PDF
  • G. Weisz, P. Budzianowski, P.-H. Su and M. Gašić, "Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces", IEEE TASLP, 2018 PDF
  • P-H. Su, M. Gašić and S. Young, "Reward Estimation for Dialogue Policy Optimisation, Computer Speech and Language", 2018 PDF
  • S. Ultes, L.M. Rojas-Barahona, P-H. Su, D. Vandyke, D. Kim, I. Casanueva, P. Budzianowski, N. Mrkšić, T-H. Wen, M. Gašić and S. Young, "PyDial: A Multi-domain Statistical Dialogue System Toolkit", ACL, Vancouver, Canada, 2017 PDF
  • P. Budzianowski, S. Ultes, P-H. Su, N. Mrkšić, T-H. Wen, I. Casanueva, L.M. Rojas-Barahona and M. Gašić, "Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning", SigDial, Saarbücken, 2017 PDF
  • P-H. Su, P. Budzianowski, S. Ultes, M. Gašić and S. Young, "Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management", SigDial, Saarbücken, 2017 PDF
  • S. Ultes, P. Budzianowski, I. Casanueva, N. Mrkšić, L.M. Rojas-Barahona, P-H. Su, T-H. Wen, M. Gašić and S. Young, "Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning", SigDial, Saarbücken, 2017 PDF
  • K. Lee, T. Zhao, Y. Du, E. Cai, A. Lu, E. Pincus, D. Traum, S. Ultes, L.M. Rojas-Barahona, M. Gašić, S. Young and M. Eskenazi, "DialPort, Gone Live: An Update After A Year of Development", SigDial, Saarbücken, 2017 PDF
  • S. Ultes, P. Budzianowski, I. Casanueva, N. Mrkšić, L.M. Rojas-Barahona, P-H. Su, T-H. Wen, M. Gašić and S. Young, "Domain-independent User Satisfaction Reward Estimation for Dialogue Policy Learning", Interspeech, Stocholm, Sweden, 2017 PDF
  • T.-H. Wen, D. Vandyke, N. Mrkšić, M. Gašić, L.M. Rojas-Barahona, P.-H. Su, S. Ultes and S. Young, "A Network-based End-to-End Trainable Task-oriented Dialogue System", EACL, pages 438-449, Valencia, Spain, 2017 PDF
  • M. Gašić, D. Hakkani-Tur and A. Celikyilmaz, "Spoken language understanding and interaction: machine learning for human-like conversational systems", Computer Speech and Language, 2017 PDF
  • N. Mrkšić, I. Vulić, D. O. Seaghdha, I. Leviant, R. Reichart, M. Gašić, A. Korhonen and S. Young. "Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints", TACL, 2017 PDF
  • M. Gašić, N. Mrkšić, L.M. Rojas-Barahona, P.-H. Su, S. Ultes, D. Vandyke, T.-H. Wen and S. Young, "Dialogue manager domain adaptation using Gaussian process reinforcement learning", Computer Speech and Language, 2017 PDF
  • L.M. Rojas-Barahona, M. Gašić, N. Mrksic, P.-H. Su, S. Ultes, T.-H. Wen and S. Young, "Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding", Coling, Osaka, Japan, 2016 PDF
  • T.-H. Wen, M. Gašić, N. Mrksic, L.M. Rojas-Barahona, P.-H. Su, S. Ultes, D. Vandyke and S. Young, "Conditional Generation and Snapshot Learning in Neural Dialogue Systems", EMNLP, Austin, USA, 2016 PDF
  • T.-H. Wen, M. Gašić, N. Mrksic, L.M. Rojas-Barahona, P.-H. Su, D. Vandyke and S. Young, "Multi-domain Neural Network Language Generation for Spoken Dialogue Systems", NAACL HLT, San Diego, USA, 2016 PDF
  • N. Mrksic, D. O Seaghdha, B. Thomson, M. Gašić, L.M. Rojas-Barahona, P.-H. Su, D. Vandyke, T.-H. Wen and S. Young, "Counter-fitting Word Vectors to Linguistic Constraints", NAACL HLT, San Diego, USA, 2016 PDF
  • P-H. Su, M. Gašić, N. Mrkšić, L.M. Rojas-Barahona, S. Ultes, D. Vandyke, T-H. Wen, and S. Young, "On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems", ACL, Berlin, 2016 [Best Student Paper Award] PDF
  • M. Gašić, N. Mrkšić, L.M. Rojas-Barahona, P-H. Su, D. Vandyke and T-H. Wen, "Multi-agent learning in multi-domain spoken dialogue systems", NIPS workshop on Spoken Language Understanding and Interaction, Montreal, Canada, 2015 PDF
  • M. Gašić, N. Mrkšić, P-H. Su, D. Vandyke, T-H. Wen and S. Young, "Policy Committee for adaptation in multi-domain spoken dialogue sytems", ASRU, Arizona, USA, 2015 [Best Paper Nomination] PDF
  • D. Vandyke, P.-H. Su, M. Gašić, N. Mrksic, T.-H. Wen and S. Young, "Multi-Domain Dialogue Success Classifiers for Policy Training", IEEE ASRU, Scottsdale, Arizona, USA, 2015 PDF
  • T.-H. Wen, M. Gašić, N. Mrksic, L. Rojas-Barahona, P.-H. Su, D. Vandyke and S. Young, "Toward Multi-domain Language Generation using Recurrent Neural Networks", NIPS Workshop on Machine Learning for Spoken Language Understanding and Interaction, Montreal, Canada, 2015 PDF
  • T-H. Wen, M. Gašić, N. Mrksic, P-H. Su, D. Vandyke and S. Young, "Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems", EMNLP, Lisbon, Portugal, 2015 [Best Paper Award] PDF
  • T-H. Wen, M. Gašić, D. Kim, N. Mrksic, P-H. Su, D. Vandyke and S. Young, "Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking", Sigdial, Prague, Czech Republic, 2015 [Best Paper Award] PDF
  • P-H. Su, D. Vandyke, M. Gašić, N. Mrksic, T-H. Wen and S. Young, "Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems", Sigdial, Prague, Czech Republic, 2015 PDF
  • N. Mrksic, D. O'Seaghdha, B. Thomson, M. Gašić, P-H. Su, D. Vandyke, T-H. Wen and S. Young, "Multi-domain Dialog State Tracking using Recurrent Neural Networks", ACL, Beijing, China, 2015 PDF
  • P-H. Su, D. Vandyke, M. Gašić, D. Kim, N. Mrksic, T-H. Wen and S. Young, "Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems", Interspeech, Dresden, 2015 PDF
  • L. Chen, P-H. Su and M. Gašić, "Hyper-parameter optimisation of Gaussian process reinforcement learning for statistical dialogue management", Proceedings of SigDial, Prague, Czech Republic, 2015 PDF
  • M. Gašić, D. Kim, P. Tsiakoulis and S. Young, "Distributed dialogue policies for multi-domain statistical dialogue management", ICASSP, Brisbane, Australia, 2015 PDF
  • M. Gašić, D. Kim, P. Tsiakoulis, C. Breslin, M. Henderson, M. Szummer, B. Thomson and S. Young. "Incremental on-line adaptation of POMDP-based dialogue managers to extended domains",Interspeech, Singapore, 2014 PDF
  • D. Kim, M. Henderson, M. Gašić, P. Tsiakoulis and S. Young, "The Use of Discriminative Belief Tracking in POMDP-based Dialogue Systems", IEEE SLT, Nevada, USA, 2014 PDF
  • D. Kim, C. Breslin, P. Tsiakoulis, M. Gašić, M. Henderson and S. Young, "Inverse Reinforcement Learning for Micro-Turn Management", Interspeech, Singapore, 2014 PDF
  • P. Tsiakoulis, C. Breslin, M. Gašić, M. Henderson, D. Kim and S. Young, "Dialogue Context Sensitive Speech Synthesis using Factorized Decision Trees", Interspeech, Singapore, 2014 PDF
  • P. Tsiakoulis, C. Breslin, M. Gašić, M. Henderson, D. Kim, M. Szummer, B. Thomson and S. Young, "Dialogue Context Sensitive HMM-Based Speech Synthesis", ICASSP, Florence, Italy, 2014 PDF
  • M. Gašić and S. Young, "Gaussian Processes for POMDP-based dialogue manager opimisation", IEEE Transactions on Audio, Speech and Language Processing, 2014 PDF
  • M. Gašić, C. Breslin, M. Henderson, D. Kim, M. Szummer, B. Thomson, P. Tsiakoulis and S. Young. "POMDP-based dialogue manager adaptation to extended domains", Sigdial, Metz, France, 2013 [Best Paper Award] PDF video
  • M. Gašić, C. Breslin, M. Henderson, D. Kim, M. Szummer, B. Thomson, P. Tsiakoulis and S. Young, "On-line policy optimisation of Bayesian spoken dialogue systems via human interaction", ICASSP, Vancouver, Canada, 2013 PDF
  • C. Breslin, M. Gašić, M. Henderson, D. Kim, M. Szummer, B. Thomson, P. Tsiakoulis and S. Young, "Continuous ASR for flexible incremental dialogue", ICASSP, Vancouver, Canada, 2013 PDF
  • M. Gašić and S. Young, "Gaussian processes for POMDP-based dialogue manager optimisation", CUED/F-INFENG/TR.684, Cambridge University Engineering Department, 2013 PDF
  • S. Young, M. Gašić, B. Thomson and J.D. Williams, "POMDP-based Statistical Spoken Dialogue Systems: a Rewiew", Special Issue of the IEEE Proceedings on Speech Information Processing - Theory and Applications, 2013 PDF
  • M. Gašić, M. Henderson, B. Thomson, P. Tsiakoulis and S. Young, "Policy optimisation of POMDP-based dialogue systems without state space compression", IEEE SLT, Miami, Florida, 2012 PDF
  • M. Gašić, P. Tsiakoulis, M. Henderson, B. Thomson, K. Yu, E. Tzirkel and S. Young, "The effect of cognitive load on a statistical dialogue system", Sigdial, Seoul, Soth Korea, 2012 PDF
  • M. Henderson, M. Gašić, B. Thomson, P. Tsiakoulis and S. Young, "Discriminative Spoken Language Understanding Using Word Confusion Networks", IEEE SLT, Miami, USA, 2012 PDF
  • B. Thomson, M. Gašić, M. Henderson, P. Tsiakoulis and S. Young, "N-Best Error Simulation for Training Spoken Dialogue Systems", IEEE SLT, Miami, USA, 2012 PDF
  • P. Tsiakoulis, M. Gašić, M. Henderson, J.Plannels-Lerma, J. Prombonas, B. Thomson, K. Yu, S. Young and E. Tzirkel, "Statistical Methods for Building Robust Spoken Dialogue Systems in an Automobile", AHFE, San Francisco, USA, 2012 PDF
  • M. Gašić, F. Jurcicek, B. Thomson and S. Young, "Optimisation for POMDP-based Spoken Dialogue Systems", Chapter 5 of "Data-driven Methods for Adaptive Spoken Dialogue Systems: Computational Learning for Conversational Interfaces", Springer, 2012 PDF
  • M. Gašić, F. Jurcicek, B. Thomson, K. Yu and S. Young, "On-line policy optimisation of spoken dialogue systems via live interaction with human subjects", ASRU,Hawaii, USA, 2011 [Honourable Mention] PDF
  • L. Daubigney, M. Gašić, S. Chandramohan, M. Geist, O. Pietquin and S. Young, "Uncertainty management for on-line optimisation of a POMDP-based large-scale spoken dialogue system", Interspeech, Florence, Italy, 2011 PDF
  • F. Jurcicek, S. Keizer, M. Gašić, F. Mairesse, B. Thomson, K. Yu and S. Young, "Real user evaluation of spoken dialogue systems using Amazon Mechanical Turk", Interspeech, Florence, Italy, 2011 PDF
  • M. Gašić and S. Young, "Effective Handling of Dialogue State in the Hidden Information State POMDP-based Dialogue Manager", ACM Transactions on Speech and Language Processing, 2011 PDF
  • M. Gašić, "Statistical Dialogue Modelling", PhD thesis, University of Cambridge, 2011 PDF
  • B. Thomson, F. Jurcicek, M. Gašić, S. Keizer, F. Mairesse, K. Yu and S. Young, "Parameter learning for POMDP spoken dialogue models", SLT, Berkeley, USA, 2010 PDF
  • B. Thomson, K. Yu, S. Keizer, M. Gašić, F. Jurcicek, F. Mairesse and S. Young, "Bayesian dialogue system for the Let's Go spoken dialogue challenge", SLT, Berkeley, USA, 2010 PDF
  • M. Gašić, F. Jurcicek, S. Keizer, F. Mairesse, B. Thomson, K. Yu and S. Young, "Gaussian Processes for Fast Policy Optimisation of POMDP-based Dialogue Managers", Sigdial, Tokyo, Japan, 2010 PDF
  • S. Keizer, M. Gašić, F. Jurcicek, F. Mairesse, B. Thomson, K. Yu and S. Young, "Parameter estimation for agenda-based user simulation", Sigdial, Tokyo, Japan, 2010 PDF
  • F. Jurcicek, B. Thomson, S. Keizer, F. Mairesse, M. Gašić, K. Yu and S. Young, "Natural Belief-Critic: a reinforcement algorithm for parameter estimation in statistical spoken dialogue systems", Interspeech, Makuhari, Japan, 2010 PDF
  • F. Mairesse, M.Gašić, F. Jurcicek, S. Keizer, J. Prombonas, B. Thomson, K. Yu and S. Young, "Phrase-based statistical language generation using graphical models and active learning", ACL, Uppsala, Sweden, 2010 PDF
  • M. Gašić and S. Young, "Effective Handling of Dialogue State in the Hidden Information State POMDP-based Dialogue Manager", CUED/F-INFENG/TR.650, Cambridge University Engineering Department, 2010 PDF
  • S. Young, M. Gašić, S. Keizer, F. Mairesse, J. Schatzmann, B. Thomson and K. Yu, "The Hidden Information State Model: a practical framework for POMDP-based spoken dialogue management", Computer Speech and Language, 24(2): 150-174, 2010 [Best Paper Award] PDF
  • M. Gašić, F. Lefevre, F. Jurcicek, S. Keizer, F. Mairesse, B. Thomson, K. Yu and S. Young, "Back-off Action Selection in Summary Space-Based POMDP Dialogue Systems", ASRU, Merano, Italy, 2009 PDF
  • F. Lefevre, M. Gašić, F. Jurcicek, S. Keizer, F. Mairesse, B. Thomson, K. Yu and S. Young, "k-Nearest Neighbor Monte-Carlo Control Algorithm for POMDP-based Dialogue Systems", Sigdial, London, UK, 2009 PDF
  • F. Jurcicek, M. Gašić, S. Keizer, F. Mairesse, B. Thomson and S. Young, "Transformation-based Learning for Semantic Parsing", Interspeech, Brighton, UK, 2009 PDF
  • K. Yu, T. Toda, M. Gašić, S. Keizer, F. Mairesse, B. Thomson and S. Young, "Probabilistic Modelling of F0 in Unvoiced Regions in HMM-based Speech Synthesis", Int Conf Acoustics Speech and Signal Processing (ICASSP), Taipei, Taiwan, 2009 PDF
  • F. Mairesse, M. Gašić, F. Jurcicek, S. Keizer, B. Thomson, K. Yu and S. Young, "Spoken Language Understanding from Unaligned Data using Discriminative Classification Models", Int Conf Acoustics Speech and Signal Processing (ICASSP), Taipei, Taiwan 2009 PDF
  • S. Keizer, M. Gašić, F. Mairesse, B. Thomson, K. Yu and S. Young, "Modelling user behaviour in the HIS-POMDP dialogue manager", SLT, Goa, India, 2008 PDF
  • B. Thomson, K. Yu, M. Gašić, S. Keizer, F. Mairesse, J. Schatzmann and S. Young, "Evaluating semantic-level confidence scores with multiple hypotheses", Interspeech, Brisbane, Australia, 2008 PDF
  • B. Thomson, M. Gašić, S. Keizer, F. Mairesse, J. Schatzmann, K.Yu and S. Young, "User study of the Bayesian Update of Dialogue State approach to dialogue management", Interspeech, Brisbane, Australia, 2008 PDF
  • M. Gašić, S. Keizer, F. Mairesse, J. Schatzmann, B. Thomson and S. Young, "Training and Evaluation of the HIS POMDP Dialogue System in Noise", Sigdial, Columbus, USA, 2008 PDF
Verantwortlichkeit: