{"type":"ScholarlyArticle","title":"Exploring Personalized Neural Conversational Models","authors":[{"name":"Satwik Kottur","slug":"satwik-kottur","given":"Satwik","family":"Kottur","affiliation":"Carnegie Mellon University , Pittsburgh , PA"},{"name":"Xiaoyu Wang","slug":"xiaoyu-wang","given":"Xiaoyu","family":"Wang","affiliation":"Snap Inc. , Venice , CA"},{"name":"Vitor Carvalho","slug":"vitor-carvalho","given":"Vitor","family":"Carvalho","affiliation":"Snap Inc. , Venice , CA"}],"abstract":"Modeling dialog systems is currently one of the most active problems in Natural Language Processing. Recent advancement in Deep Learning has sparked an interest in the use of neural networks in modeling language, particularly for personalized conversational agents that can retain contextual information during dialog exchanges. This work carefully explores and compares several of the recently proposed neural conversation models, and carries out a detailed evaluation on the multiple factors that can significantly affect predictive performance, such as pretraining, embedding training, data cleaning, diversity reranking, evaluation setting, etc. Based on the tradeoffs of different models, we propose a new generative dialogue model conditioned on speakers as well as context history that outperforms all previous models on both retrieval and generative metrics. Our findings indicate that pretraining speaker embeddings on larger datasets, as well as bootstrapping word and speaker embeddings, can significantly improve performance (up to 3 points in perplexity), and that promoting diversity in using Mutual Information based techniques has a very strong effect in ranking metrics.","doi":"10.24963/ijcai.2017/521","url":"https://ijcai.org/proceedings/2017/521","pdf":"https://ijcai.org/proceedings/2017/0521.pdf","markdown":"https://ijcai.org/proceedings/2017/521.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/521","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Multidisciplinary Topics and Applications","track":"Main track","number":521,"pages":{"first":3728,"last":3734},"keywords":["Natural Language Processing: Dialogue","Natural Language Processing: Natural Language Generation","Multidisciplinary Topics and Applications: Personalization and User Modeling"],"videos":[],"references":[{"position":1,"raw":"[Al-Rfou et al., 2016] Rami Al-Rfou, Marc Pickett, Javier Snaider, Yun-hsuan Sung, Brian Strope, and Ray Kurzweil. Conversational contextual cues: The case of personalization and history for response ranking. arXiv preprint arXiv:1606.00372, 2016.","title":"Conversational contextual cues: The case of personalization and history for response ranking","authors":"Rami Al-Rfou, Marc Pickett, Javier Snaider, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ameixa et al., 2014] David Ameixa, Luisa Coheur, Pedro Fialho, and Paulo Quaresma. Luke, I am Your Father: Dealing with Out-of-Domain Requests by Using Movies Subtitles, pages 13-21. Cham, 2014.","title":"I am Your Father: Dealing with Out-of-Domain Requests by Using Movies Subtitles","authors":"David Ameixa, Luisa Coheur, Pedro Fialho, Paulo Quaresma, Luke","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Banchs, 2012] Rafael E. Banchs. Movie-DiC: a movie dia- logue corpus for research and development. In ACL, pages 203-207, Jeju Island, Korea, July 2012.","title":"Movie-DiC: a movie dialogue corpus for research and development","authors":"Rafael E Banchs","year":"2012","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bengio et al., 2003] Yoshua Bengio, Réjean Ducharme, Pascal Vincent, and Christian Jauvin. A neural probabilis- tic language model. JMLR, 3(Feb):1137-1155, 2003.","title":"A neural probabilistic language model","authors":"Yoshua Bengio, Réjean Ducharme, Pascal Vincent, Christian Jauvin","year":"2003","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bird et al., 2009] Steven Bird, Ewan Klein, and Edward Loper. Natural Language Processing with Python.","title":"Natural Language Processing with Python","authors":"Steven Bird, Ewan Klein, Edward Loper","year":null,"venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"O'Reilly Media, 2009.","title":null,"authors":"O, Reilly Media","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chelba et al., 2013] Ciprian Chelba, Tomas Mikolov, Mike Schuster, Qi Ge, Thorsten Brants, Phillipp Koehn, and Tony Robinson. One billion word benchmark for measur- ing progress in statistical language modeling. Technical report, Google, 2013.","title":"One billion word benchmark for measuring progress in statistical language modeling","authors":"Ciprian Chelba, Tomas Mikolov, Mike Schuster, Qi Ge, Thorsten Brants, Phillipp Koehn, Tony Robinson","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart Van Merriënboer, C ¸alar Gülc ¸ehre, Dzmitry Bahdanau, Fethi Bougares, Hol- ger Schwenk, and Yoshua Bengio. Learning phrase rep- resentations using rnn encoder-decoder for statistical ma- chine translation. In EMNLP, pages 1724-1734, Doha, Qatar, October 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Collobert et al., 2011] R. Collobert, K. Kavukcuoglu, and C. Farabet. Torch7: A matlab-like environment for ma- chine learning. In BigLearn, NIPS Workshop, 2011.","title":"Torch7: A matlab-like environment for machine learning","authors":"R Collobert, K Kavukcuoglu, C Farabet","year":"2011","venue":"BigLearn, NIPS Workshop","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Forchini, 2009] P. Forchini. Spontaneity reloaded: Amer- ican face-to-face and movie conversation compared. In Corpus Linguistics 2009. Abstracts of the Corpus Linguis- tics Conference, 2009.","title":"Spontaneity reloaded: American face-to-face and movie conversation compared","authors":"P Forchini","year":"2009","venue":"Abstracts of the Corpus Linguistics Conference","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Galley et al., 2015] Michel Galley, Chris Brockett, Alessan- dro Sordoni, Yangfeng Ji, Michael Auli, Chris Quirk, Mar- garet Mitchell, Jianfeng Gao, and Bill Dolan. deltableu: A discriminative metric for generation tasks with intrin- sically diverse targets. In ACL, pages 445-450, Beijing, China, July 2015.","title":"deltableu: A discriminative metric for generation tasks with intrinsically diverse targets","authors":"Michel Galley, Chris Brockett, Alessandro Sordoni, Yangfeng Ji, Michael Auli, Chris Quirk, Margaret Mitchell, Jianfeng Gao, Bill Dolan","year":"2015","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kannan et al., 2016] Anjuli Kannan, Karol Kurach, Sujith Ravi, Tobias Kaufman, Balint Miklos, Greg Corrado, Andrew Tomkins, Laszlo Lukacs, Marina Ganea, Peter Young, and Vivek Ramavajjala. Smart reply: Automated response suggestion for email. In KDD (2016)., 2016.","title":"Smart reply: Automated response suggestion for email","authors":"Anjuli Kannan, Karol Kurach, Sujith Ravi, Tobias Kaufman, Balint Miklos, Greg Corrado, Andrew Tomkins, Laszlo Lukacs, Marina Ganea, Peter Young, Vivek Ramavajjala","year":"2016","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kingma and Ba, 2014] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. CoRR, abs/1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kneser and Ney, 1995] R. Kneser and H. Ney. Improved backing-off for m-gram language modeling. ICASSP, 1:181-184, 1995.","title":"Improved backing-off for m-gram language modeling","authors":"R Kneser, H Ney","year":"1995","venue":"ICASSP","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2016a] Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. A diversity-promoting objective function for neural conversation models. In NAACL, pages 110-119, 2016.","title":"A diversity-promoting objective function for neural conversation models","authors":"Li","year":"2016","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li et al., 2016b] Jiwei Li, Michel Galley, Chris Brockett, Georgios Spithourakis, Jianfeng Gao, and Bill Dolan. A persona-based neural conversation model. In ACL, pages 994-1003, 2016.","title":"A persona-based neural conversation model","authors":"Li","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2016] Chia-Wei Liu, Ryan Lowe, Iulian V Ser- ban, Michael Noseworthy, Laurent Charlin, and Joelle Pineau. How not to evaluate your dialogue system: An empirical study of unsupervised evaluation met- rics for dialogue response generation. arXiv preprint arXiv:1603.08023, 2016.","title":"How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation","authors":"Chia-Wei Liu, Ryan Lowe, Michael Iulian V Serban, Laurent Noseworthy, Joelle Charlin, Pineau","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Lowe et al., 2015] Ryan Lowe, Nissan Pow, Iulian Serban, and Joelle Pineau. The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems. arXiv preprint arXiv:1506.08909, 2015.","title":"The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems","authors":"Ryan Lowe, Nissan Pow, Iulian Serban, Joelle Pineau","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Mikolov and Dean, 2013] T Mikolov and J Dean. Dis- tributed representations of words and phrases and their compositionality. Advances in NIPS, 2013.","title":"Distributed representations of words and phrases and their compositionality","authors":"T Mikolov, Dean","year":"2013","venue":"Advances in NIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ritter et al., 2011] Alan Ritter, Colin Cherry, and William B Dolan. Data-driven response generation in social media. In EMNLP, pages 583-593, 2011.","title":"Data-driven response generation in social media","authors":"Alan Ritter, Colin Cherry, William B Dolan","year":"2011","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Serban et al., 2015a] Iulian V Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, and Joelle Pineau. Hier- archical neural network generative models for movie dia- logues. arXiv preprint arXiv:1507.04808, 2015.","title":"Hierarchical neural network generative models for movie dialogues","authors":"Serban","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Serban et al., 2015b] Iulian Vlad Serban, Alessandro Sor- doni, Yoshua Bengio, Aaron C. Courville, and Joelle Pineau. Hierarchical neural network generative models for movie dialogues. CoRR, abs/1507.04808, 2015.","title":"Hierarchical neural network generative models for movie dialogues","authors":"Serban","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Serban et al., 2016a] Iulian Vlad Serban, Alberto García- Durán, Caglar Gulcehre, Sungjin Ahn, Sarath Chan- dar, Aaron Courville, and Yoshua Bengio. Generating factoid questions with recurrent neural networks: The 30m factoid question-answer corpus. arXiv preprint arXiv:1603.06807, 2016.","title":"Generating factoid questions with recurrent neural networks: The 30m factoid question-answer corpus","authors":"Serban","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Serban et al., 2016b] Iulian Vlad Serban, Alessandro Sor- doni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron Courville, and Yoshua Bengio. A hierarchical latent variable encoder-decoder model for generating dialogues. arXiv preprint arXiv:1605.06069, 2016.","title":"A hierarchical latent variable encoder-decoder model for generating dialogues","authors":"Serban","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sordoni et al., 2015] Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, and Bill Dolan. A neural network approach to context-sensitive generation of conversational responses. In NAACL, pages 196-205, Denver, Colorado, May-June 2015.","title":"A neural network approach to context-sensitive generation of conversational responses","authors":"Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, Bill Dolan","year":"2015","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Srivastava et al., 2014] Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdi- nov. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res., 15(1):1929-1958, January 2014.","title":"Dropout: A simple way to prevent neural networks from overfitting","authors":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov","year":"2014","venue":"J. Mach. Learn. Res","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Sutskever et al., 2014] Ilya Sutskever, Oriol Vinyals, and Quoc V Le. Sequence to sequence learning with neural networks. In Advances in NIPS, pages 3104-3112, 2014.","title":"Quoc V Le. Sequence to sequence learning with neural networks","authors":"Sutskever","year":"2014","venue":"Advances in NIPS","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Vinyals and Le, 2015] Oriol Vinyals and Quoc V. Le. A neural conversational model. CoRR, abs/1506.05869, 2015.","title":"A neural conversational model","authors":"Oriol Vinyals, V Quoc, Le","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wen et al., 2015] Tsung-Hsien Wen, Milica Gasic, Dongho Kim, Nikola Mrksic, Pei-Hao Su, David Vandyke, and Steve Young. Stochastic language generation in dialogue using recurrent neural networks with convolutional sen- tence reranking. arXiv preprint arXiv:1508.01755, 2015.","title":"Stochastic language generation in dialogue using recurrent neural networks with convolutional sentence reranking","authors":"Tsung-Hsien Wen, Milica Gasic, Dongho Kim, Nikola Mrksic, Pei-Hao Su, David Vandyke, Steve Young","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}