Publications

Enhancing abstractiveness of summarization models through calibrated distillation

Published in In the proceedings of Findings of EMNLP 2023, 2023

Access paper here

Recommended citation: Hwanjun Song, Igor Shalyminov, Hang Su, Siffi Singh, Kaisheng Yao, Saab Mansour, "Enhancing abstractiveness of summarization models through calibrated distillation." In the proceedings of Findings of EMNLP 2023, 2023. https://www.amazon.science/publications/enhancing-abstractiveness-of-summarization-models-through-calibrated-distillation

Fast Domain Adaptation for Goal-Oriented Dialogue Using a Hybrid Generative-Retrieval Transformer

Published in In the proceedings of ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020

Use Google Scholar for full citation

Recommended citation: I. {Shalyminov}, A. {Sordoni}, A. {Atkinson}, H. {Schulz}, "Fast Domain Adaptation for Goal-Oriented Dialogue Using a Hybrid Generative-Retrieval Transformer." In the proceedings of ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020.

Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach

Published in In the proceedings of Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, 2019

Access paper here

Recommended citation: Igor Shalyminov, Sungjin Lee, Arash Eshghi, Oliver Lemon, "Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach." In the proceedings of Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, 2019. https://www.aclweb.org/anthology/W19-5904

Contextual Out-of-domain Utterance Handling with Counterfeit Data Augmentation

Published in In the proceedings of ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019

Use Google Scholar for full citation

Recommended citation: S. {Lee}, I. {Shalyminov}, "Contextual Out-of-domain Utterance Handling with Counterfeit Data Augmentation." In the proceedings of ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019.

Data-Efficient Goal-Oriented Conversation with Dialogue Knowledge Transfer Networks

Published in In the proceedings of Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, 2019

Access paper here

Recommended citation: Igor Shalyminov, Sungjin Lee, Arash Eshghi, Oliver Lemon, "Data-Efficient Goal-Oriented Conversation with Dialogue Knowledge Transfer Networks." In the proceedings of Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, 2019. https://doi.org/10.18653/v1/D19-1183

Neural Response Ranking for Social Conversation: A Data-Efficient Approach

Published in In the proceedings of Proceedings of the 2nd International Workshop on Search-Oriented Conversational AI, SCAI@EMNLP 2018, Brussels, Belgium, October 31, 2018, 2018

Access paper here

Recommended citation: Igor Shalyminov, Ondrej Dusek, Oliver Lemon, "Neural Response Ranking for Social Conversation: A Data-Efficient Approach." In the proceedings of Proceedings of the 2nd International Workshop on Search-Oriented Conversational AI, SCAI@EMNLP 2018, Brussels, Belgium, October 31, 2018, 2018. https://aclanthology.info/papers/W18-5701/w18-5701

Multi-Task Learning for Domain-General Spoken Disfluency Detection in Dialogue Systems

Published in In the proceedings of Proceedings of the 22st Workshop on the Semantics and Pragmatics of Dialogue (SemDial 2018 - AixDial), 2018

Use Google Scholar for full citation

Recommended citation: Igor Shalyminov, Arash Eshghi, Oliver Lemon, "Multi-Task Learning for Domain-General Spoken Disfluency Detection in Dialogue Systems." In the proceedings of Proceedings of the 22st Workshop on the Semantics and Pragmatics of Dialogue (SemDial 2018 - AixDial), 2018.

Improving Robustness of Neural Dialog Systems in a Data-Efficient Way with Turn Dropout

Published in The Second NeurIPS Workshop on Conversational AI: ``Today's Practice and Tomorrow's Potential'', 2018

Access paper here

Recommended citation: Igor Shalyminov, Sungjin Lee, "Improving Robustness of Neural Dialog Systems in a Data-Efficient Way with Turn Dropout." The Second NeurIPS Workshop on Conversational AI: ``Today's Practice and Tomorrow's Potential'', 2018. http://arxiv.org/abs/1811.12148

Alana v2: Entertaining and Informative Open-domain Social Dialogue using Ontologies and Entity Linking

Published in In the proceedings of 2018 Alexa Prize Proceedings, 2018

Use Google Scholar for full citation

Recommended citation: Amanda Curry, Ioannis Papaioannou, Alessandro Suglia, Shubham Agarwal, Igor Shalyminov, Xinnuo Xu, Ondrej Dusek, Arash Eshghi, Ionnis Konstas, Verena Rieser, Oliver Lemon, "Alana v2: Entertaining and Informative Open-domain Social Dialogue using Ontologies and Entity Linking." In the proceedings of 2018 Alexa Prize Proceedings, 2018.

Challenging Neural Dialogue Models with Natural Data: Memory Networks Fail on Incremental Phenomena

Published in In the proceedings of Proceedings of the 21st Workshop on the Semantics and Pragmatics of Dialogue (SemDial 2017 - SaarDial), 2017

Use Google Scholar for full citation

Recommended citation: Igor Shalyminov, Arash Eshghi, Oliver Lemon, "Challenging Neural Dialogue Models with Natural Data: Memory Networks Fail on Incremental Phenomena." In the proceedings of Proceedings of the 21st Workshop on the Semantics and Pragmatics of Dialogue (SemDial 2017 - SaarDial), 2017.

Bootstrapping incremental dialogue systems from minimal data: the generalisation power of dialogue grammars

Published in In the proceedings of Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017, 2017

Access paper here

Recommended citation: Arash Eshghi, Igor Shalyminov, Oliver Lemon, "Bootstrapping incremental dialogue systems from minimal data: the generalisation power of dialogue grammars." In the proceedings of Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017, 2017. https://aclanthology.info/papers/D17-1236/d17-1236

Bootstrapping dialogue systems: the contribution of a semantic model of interactional dynamics

Published in In the proceedings of Proceedings of the Conference on Logic and Machine Learning in Natural Language (LaML 2017), 2017

Use Google Scholar for full citation

Recommended citation: Arash Eshghi, Igor Shalyminov, Oliver Lemon, "Bootstrapping dialogue systems: the contribution of a semantic model of interactional dynamics." In the proceedings of Proceedings of the Conference on Logic and Machine Learning in Natural Language (LaML 2017), 2017.