{"type":"ScholarlyArticle","title":"Using a Deep Learning Dialogue Research Toolkit in a Multilingual Multidomain Practical Application","authors":[{"name":"Graham Wilcock","slug":"graham-wilcock","given":"Graham","family":"Wilcock","affiliation":"CDM Interact , Helsinki , Finland"}],"abstract":"The demo shows a practical application of an open-source research toolkit developed by University of Cambridge. The toolkit (PyDial) supports research on deep reinforcement learning for multi-domain dialogues. The application (CityTalk) is a spoken dialogue system for robots that give information to tourists about local hotels and restaurants. We had a very positive experience using the toolkit, but in a few areas we decided to do things our own way.","doi":"10.24963/ijcai.2018/869","url":"https://ijcai.org/proceedings/2018/869","pdf":"https://ijcai.org/proceedings/2018/0869.pdf","markdown":"https://ijcai.org/proceedings/2018/869.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/869","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Demos","track":"Demos","number":869,"pages":{"first":5880,"last":5882},"keywords":["Natural Language Processing: NLP Applications and Tools","Natural Language Processing: Dialogue","Natural Language Processing: Speech","Robotics and Vision: Human Robot Interaction"],"videos":[],"references":[{"position":1,"raw":"[Casanueva et al., 2017] Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su, Nikola Mrkšić, Tsung-Hsien Wen, Stefan Ultes, Lina M. Rojas Barahona, Steve Young, and Milica Gasic. A benchmarking environment for reinforcement learning based task oriented dialogue man- agement. [arXiv], 2017. https://arxiv.org/abs/1711.11023.","title":"A benchmarking environment for reinforcement learning based task oriented dialogue management","authors":"Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su, Nikola Mrkšić, Tsung-Hsien Wen, Stefan Ultes, Lina M Rojas Barahona, Steve Young, Milica Gasic","year":"2017","venue":null,"doi":null,"url":"https://arxiv.org/abs/1711.11023","internal_url":null},{"position":2,"raw":"[Gasic et al., 2015] Milica Gasic, Nikola Mrkšić, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, and Steve Young. Policy committee for adaptation in multi-domain spoken dialogue systems. In 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Scotts- dale, AZ, 2015. IEEE.","title":"Policy committee for adaptation in multi-domain spoken dialogue systems","authors":"Milica Gasic, Nikola Mrkšić, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, Steve Young","year":"2015","venue":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Higashinaka et al., 2016] Ryuichiro Higashinaka, Nozomi Kobayashi, Toru Hirano, Chiaki Miyazaki, Toyomi Me- guro, Toshiro Makino, and Yoshihiro Matsuo. Syntac- tic filtering and content-based retrieval of twitter sen- tences for the generation of system utterances in dia- logue systems. In Alexander Rudnicky, Antoine Raux, Ian Lane, and Teruhisa Misu, editors, Situated Dialog in Speech-Based Human-Computer Interaction, pages 15- 26. Springer, 2016.","title":"Syntactic filtering and content-based retrieval of twitter sentences for the generation of system utterances in dialogue systems","authors":"Ryuichiro Higashinaka, Nozomi Kobayashi, Toru Hirano, Chiaki Miyazaki, Toyomi Meguro, Toshiro Makino, Yoshihiro Matsuo","year":"2016","venue":"Situated Dialog in Speech-Based Human-Computer Interaction","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Jokinen and Wilcock, 2014] Kristiina Jokinen and Graham Wilcock. Multimodal open-domain conversations with the Nao robot. In Joseph Mariani, Sophie Rosset, Mar- tine Garnier-Rizet, and Laurence Devillers, editors, Natu- ral Interaction with Robots, Knowbots and Smartphones: Putting Spoken Dialogue Systems into Practice, pages 213-224. Springer, 2014.","title":"Multimodal open-domain conversations with the Nao robot","authors":"Jokinen, Wilcock, Kristiina Jokinen, Graham Wilcock","year":"2014","venue":"Natural Interaction with Robots, Knowbots and Smartphones: Putting Spoken Dialogue Systems into Practice","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Laxström et al., 2017] Niklas Laxström, Graham Wilcock, and Kristiina Jokinen. Internationalisation and localisa- tion of spoken dialogue systems. In Kristiina Jokinen and Graham Wilcock, editors, Dialogues with Social Robots: Enablements, Analyses, and Evaluation, pages 207-219. Springer, 2017.","title":"Internationalisation and localisation of spoken dialogue systems","authors":"Laxström","year":"2017","venue":"Dialogues with Social Robots: Enablements, Analyses, and Evaluation","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Mrkšić et al., 2015] Nikola Mrkšić, Diarmuid Ó Seaghdha, Blaise Thomson, Milica Gasic, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, and Steve Young. Multi- domain dialog state tracking using recurrent neural net- works. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, pages 794- 799, Beijing, China, July 2015. Association for Computa- tional Linguistics.","title":"Multidomain dialog state tracking using recurrent neural networks","authors":"Nikola Mrkšić, Ó Diarmuid, Blaise Seaghdha, Milica Thomson, Pei-Hao Gasic, David Su, Tsung-Hsien Vandyke, Steve Wen, Young","year":"2015","venue":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Mrkšić et al., 2017] Nikola Mrkšić, Diarmuid Ó Seaghdha, Tsung-Hsien Wen, Blaise Thomson, and Steve Young. Neural belief tracker: Data-driven dialogue state tracking. In Proceedings of the 55th Annual Meeting of the Asso- ciation for Computational Linguistics, pages 1777-1788, Vancouver, Canada, July 2017. Association for Computa- tional Linguistics.","title":"Neural belief tracker: Data-driven dialogue state tracking","authors":"Nikola Mrkšić, Ó Diarmuid, Tsung-Hsien Seaghdha, Blaise Wen, Steve Thomson, Young","year":"2017","venue":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Rojas Barahona et al., 2016] Lina M. Rojas Barahona, Mil- ica Gasic, Nikola Mrkšić, Pei-Hao Su, Stefan Ultes, Tsung-Hsien Wen, and Steve Young. Exploiting sentence and context representations in deep neural models for spo- ken language understanding. In Proceedings of COL- ING 2016, the 26th International Conference on Computa- tional Linguistics: Technical Papers, pages 258-267, Os- aka, Japan, 2016. Association for Computational Linguis- tics.","title":"Exploiting sentence and context representations in deep neural models for spoken language understanding","authors":"Lina M Rojas Barahona, Milica Gasic, Nikola Mrkšić, Pei-Hao Su, Stefan Ultes, Tsung-Hsien Wen, Steve Young","year":"2016","venue":"Proceedings of COL-ING 2016, the 26th International Conference on Computa-tional Linguistics: Technical Papers","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Ultes et al., 2017] Stefan Ultes, Lina M. Rojas Bara- hona, Pei-Hao Su, David Vandyke, Dongho Kim, Iñigo Casanueva, Paweł Budzianowski, Nikola Mrkšić, Tsung- Hsien Wen, Milica Gasic, and Steve Young. PyDial: A Multi-domain Statistical Dialogue System Toolkit. In Pro- ceedings of ACL 2017, System Demonstrations, pages 73- 78, Vancouver, Canada, July 2017. Association for Com- putational Linguistics.","title":"PyDial: A Multi-domain Statistical Dialogue System Toolkit","authors":"Stefan Ultes, Lina M Rojas Barahona, Pei-Hao Su, David Vandyke, Dongho Kim, Iñigo Casanueva, Paweł Budzianowski, Nikola Mrkšić, Tsung-Hsien Wen, Milica Gasic, Steve Young","year":"2017","venue":"Proceedings of ACL 2017, System Demonstrations","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Wen et al., 2015] Tsung-Hsien Wen, Milica Gasic, Nikola Mrkšić, Pei-Hao Su, David Vandyke, and Steve Young. Semantically conditioned LSTM-based natural language generation for spoken dialogue systems. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1711-1721, Lisbon, Portu- gal, 2015. Association for Computational Linguistics.","title":"Semantically conditioned LSTM-based natural language generation for spoken dialogue systems","authors":"Tsung-Hsien Wen, Milica Gasic, Nikola Mrkšić, Pei-Hao Su, David Vandyke, Steve Young","year":"2015","venue":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Wen et al., 2016] Tsung-Hsien Wen, Milica Gasic, Nikola Mrkšić, Lina M. Rojas Barahona, Pei-Hao Su, David Vandyke, and Steve Young. Multi-domain neural net- work language generation for spoken dialogue systems. In Proceedings of NAACL-HLT 2016, pages 120-129, San Diego, California, 2016. Association for Computational Linguistics.","title":"Multi-domain neural network language generation for spoken dialogue systems","authors":"Tsung-Hsien Wen, Milica Gasic, Nikola Mrkšić, Lina M Rojas Barahona, Pei-Hao Su, David Vandyke, Steve Young","year":"2016","venue":"Proceedings of NAACL-HLT 2016","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Wilcock et al., 2016] Graham Wilcock, Kristiina Jokinen, and Seiichi Yamamoto. What topic do you want to hear about? A bilingual talking robot using English and Japanese Wikipedias. In Proceedings of COLING 2016, the 26th International Conference on Computational Lin- guistics: System Demonstrations, Osaka, Japan, 2016. As- sociation for Computational Linguistics.","title":"What topic do you want to hear about? A bilingual talking robot using English and Japanese Wikipedias","authors":"Graham Wilcock, Kristiina Jokinen, Seiichi Yamamoto","year":"2016","venue":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Wilcock, 2012] Graham Wilcock. WikiTalk: A spoken Wikipedia-based open-domain knowledge access system. In Proceedings of the COLING 2012 Workshop on Ques- tion Answering for Complex Domains, pages 57-69, Mumbai, India, 2012. Association for Computational Lin- guistics.","title":"WikiTalk: A spoken Wikipedia-based open-domain knowledge access system","authors":"Graham Wilcock","year":"2012","venue":"Proceedings of the COLING 2012 Workshop on Question Answering for Complex Domains","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Wilcock, 2017] Graham Wilcock. CDM CityTalk: The robot gives information about hotels and restaurants in Cambridge. [YouTube video], 2017. https://youtu.be/ zWdd7kv5sX8.","title":"CDM CityTalk: The robot gives information about hotels and restaurants in Cambridge","authors":"Graham Wilcock","year":"2017","venue":null,"doi":null,"url":"https://youtu.be/zWdd7kv5sX8","internal_url":null},{"position":15,"raw":"[Wilcock, 2018a] Graham Wilcock. CDM CityTalk: The robot gives information about several hotels and restau- rants in Tokyo Waterfront. [YouTube video], 2018. https: //youtu.be/OhjIJp8XBEA.","title":"CDM CityTalk: The robot gives information about several hotels and restaurants in Tokyo Waterfront","authors":"Graham Wilcock, Wilcock","year":"2018","venue":null,"doi":null,"url":"https://youtu.be/OhjIJp8XBEA","internal_url":null},{"position":16,"raw":"[Wilcock, 2018b] Graham Wilcock. CityTalk: Robots that talk to tourists and can switch domains during the dia- logue. In Ninth International Workshop on Spoken Dia- logue Systems (IWSDS 2018), Singapore, 2018.","title":"CityTalk: Robots that talk to tourists and can switch domains during the dialogue","authors":"Graham Wilcock, Wilcock","year":"2018","venue":"Ninth International Workshop on Spoken Dialogue Systems (IWSDS 2018)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}