2nd Conversational AI:
“Today's Practice and Tomorrow's Potential”

NeurIPS 2018 - Workshop



In the span of only a few years, conversational systems have become commonplace. Every day, millions of people use natural-language interfaces such as Siri, Google Now, Cortana, Alexa and others via in-home devices, phones, or messaging channels such as Messenger, Slack, Skype, among others.  At the same time, interest among the research community in conversational systems has blossomed: for supervised and reinforcement learning, conversational systems often serve as both a benchmark task and an inspiration for new ML methods at conferences which don't focus on speech and language per se, such as NeurIPS, ICML, IJCAI, and others.  Research community challenge tasks are proliferating, including the seventh Dialog Systems Technology Challenge (DSTC7), the Amazon Alexa prize, and the Conversational Intelligence Challenge live competitions at NeurIPS (2017, 2018).

Following the overwhelming participation in our last year NeurIPS workshop (9 invited talks, 26 submissions, 3 orals papers, 13 accepted papers, 37 PC members, and couple of hundreds of participants), we are excited to continue promoting cross-pollination of ideas between academic research centers and industry. The goal of this workshop is to bring together researchers and practitioners in this area, to clarify impactful research problems, share findings from large-scale real-world deployments, and generate new ideas for future lines of research.

This workshop will include invited talks, contributed work, and open discussion.  In these talks, senior technical leaders from both academia and industry will give insights into real usage and challenges at scale.  An open call for papers will be issued, and we will prioritize forward-looking papers that propose interesting and impactful contributions.  We will end the day with an open discussion, including a panel consisting of academic and industrial researchers.

Invited Speakers

  1. Mari Ostendorf (University of Washington)

  2. Alexander Rudnicky (Carnegie Mellon University)

  3. Ruhi Sarikaya (Amazon)

  4. Lazaros C Polymenakos (IBM)



Call for Papers

We invite you to submit your contributions here in the area of conversational AI by October 25th 11:59 PM EST in NeurIPS style with maximum of 8 pages excluding the references. You can add supplementary material in addition to 8 pages, but reviewers are not required to review the extra material (e.g. your paper should stand on its own without the supplementary material).  Notifications will be sent out by November 21st. Selected papers will be presented through invited talks or posters. Maximum allowed size of posters is 36 x 48 inch (91 x 122 cm). Notice that our workshop is not archival. However, accepted submission will be hosted on this website similar to last year’s workshop. Given authors concern around posting their submissions to arXiv the organizing committed decided to lift the anonymity requirement for our workshop. This means the anonymity will be optional and decided by the authors. Hence, you can post your submissions to arXiv. For further questions, feel free to reach out to co-chairs through email.

Important Dates

Submission:                              25 October 2018 11:59 PM EST (link)

Notification:                             21 November 2018

Camera Ready:                        28 November 2018

Registration:                             see NeurIPS website

Workshop:                                7 December 2018

Palais des Congrès de Montréal, Montréal, Canada - Room 519


9:00-9:10        Opening Remarks (Alborz Geramifard)

9:10-9:40        Invited Talk: Modeling the User in Socialbot Conversations (Mari Ostendorf)

9:40-10:10      Invited Talk: Friction-Free Contextual Conversational AI (Ruhi Sarikaya)

10:10-10:30    Poster Blitz

10:30-11:00    Coffee Break / Hangup Posters

11:00-11:20    Contributed Talk: Cross-lingual Transfer Learning for Multilingual Task Oriented Dialog

11:20-11:40    Contributed Talk: DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks (Winner of Best Paper Award)
11:40-12:10    Invited Talk:
Conversational moves and blended conversation (Alexander Rudnicky)

12:10-1:50      Lunch Break

1:50-2:20        Invited Talk: Knowledge Grounded End-to-End Dialog (Lazaros Polymenakos)

2:20-2:40        Contributed Talk: Improving Semantic Parsing for Task Oriented Dialog

2:40-3:00        Contributed Talk: Dialog System Technology Challenge 7

3:00-3:50        Coffee Break / Poster Session

3:50-4:10        Contributed Talk: Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
4:10-4:30        Contributed Talk: Can You be More Polite and Positive? Infusing Social Language into Task-Oriented Conversational Agents

4:30-5:25        Panel / Open Discussion - All Organizers (submit questions here)

5:25-5:30        Closing Remarks (Jason Williams)

Questions for Panel

Best Paper Award

Congratulations to Semih Yavuz, Abhinav Rastogi, Guan-lin Chao and Dilek Hakkani-Tür for winning our Best Paper Award!

Accepted Papers - Talk

  1. Dialog System Technology Challenge 7 [PDF]
    Koichiro Yoshino, Chiori Hori, Julien Perez, Luis Fernando D’Haro, Lazaros Polymenakos, Chulaka Gunasekara, Walter S. Lasecki, Jonathan K. Kummerfeld, Michel Galley, Chris Brockett, Jianfeng Gao, Bill Dolan, Xiang Gao, Huda Alamari, Tim K. Marks, Devi Parikh and Dhruv Batra

  2. Improving Semantic Parsing for Task Oriented Dialog [PDF]
    Arash Einolghozati, Panupong Pasupat, Sonal Gupta, Rushin Shah, Mrinal Mohit, Mike Lewis and Luke Zettlemoyer

  3. DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks (winner of Best Paper Award) [PDF]
    Semih Yavuz, Abhinav Rastogi, Guan-lin Chao and Dilek Hakkani-Tür

  4. Can You be More Polite and Positive? Infusing Social Language into Task-Oriented Conversational Agents [PDF]
    Yi-Chia Wang, Runze Wang, Gokhan Tur, Hugh Williams

  5. Cross-lingual Transfer Learning for Multilingual Task Oriented Dialog [PDF]
    Sebastian Schuster, Sonal Gupta, Rushin Shah, Mike Lewis

  6. Global-to-local Memory Pointer Networks for Task-Oriented Dialogue [PDF]
    Chien-Sheng Wu, Caiming Xiong and Richard Socher

Accepted Papers - Poster

  1. 1.Improving Robustness of Dialog Systems in a Data-Efficient Way with Turn Dropout [PDF]
    Igor Shalyminov and Sungjin Lee

  2. 2.A Study on Dialogue Reward Prediction for Open-Ended Conversational Agents [PDF]
    Heriberto Cuayáhuitl, Seonghan Ryu, Donghyeon Lee and Jihie Kim

  3. 3.Few-Shot Generalization Across Dialogue Tasks [PDF]
    Vladimir Vlasov, Akela Drissner-Schmid and Alan Nichol

  4. 4.Detecting Offensive Content in Open-domain Conversations using Two Stage Semi-supervision [PDF]
    Chandra Khatri, Behnam Hedayatnia, Rahul Goel Anushree Venkatesh, Raefer Gabriel and Arindam Mandal

  5. 5.Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems [PDF]
    Rahul Goel, Shachi Paul, Tagyoung Chung Jeremie Lecomte, Arindam Mandal and Dilek Hakkani-Tur

  6. 6.Modeling Non-Goal Oriented Dialog With Discrete Attributes [PDF]
    Chinnadhurai Sankar and Sujith Ravi

  7. 7.An Interpretable (Conversational) VQA model using Attention based Weighted Contextual Features [PDF]
    Yu Wang, Abhishek Patel, Yilin Shen, Hongxia Jin and Larry Heck

  8. 8.Wizard of Wikipedia: Knowledge-powered Conversational agents [PDF]
    Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli and Jason Weston

  9. 9.A Bandit Approach to Posterior Dialog Orchestration Under a Budget [PDF]
    Sohini Upadhyay, Mayank Agarwal, Djallel Bounneffouf, and Yasaman Khazaeni

  10. 10.Cross-Lingual Approaches to Reference Resolution in Dialogue Systems [PDF]
    Amr Sharaf, Arpit Gupta, Hancheng Ge, Chetan Naik and Lambert Mathias

  11. 11.On Modelling Uncertainty in Neural Language Generation for Policy Optimisation in Voice-Triggered Dialog Assistants [PDF]
    Sihui Wang, Tom Gunter, David VanDyke, Thomas Voice and Blaise Thomson

  12. 12.Toward Scalable Neural Dialogue State Tracking Model [PDF]
    Elnaz Nouri and Ehsan Hosseini-Asl

  13. 13.Incorporating the Structure of the Belief State in End-to-End Task-Oriented Dialogue Systems [PDF]
    Lei Shu, Piero Molino, Mahdi Namazifar, Bing Liu, Hu Xu, Huaixiu Zheng and Gokhan Tur

  14. 14.A Multimodal Dialogue System for Conversational Image Editing [PDF]
    Tzu-Hsiang Lin, Trung Bui, Doo Soon Kim and Jean Oh

  15. 15.Leveraging User Engagement Signals For Entity Labeling in a Virtual Assistant [PDF]
    Deepak Muralidharan, Justine Kao, Xiao Yang, Lin Li, Lavanya Viswanathan, Mubarak Seyed Ibrahim, Kevin Luikens, Stephen Pulman, Ashish Garg, Atish Kothari and Jason Wiiliams

  16. 16.Neural Machine Translation for Paraphrase Generation [PDF]
    Alex Sokolov and Denis Filimonov

  17. 17.TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents [PDF]
    Thomas Wolf, Victor Sanh, Julien Chaumond and Clement Delangue

Program Committee

  1. Murat Akbacak (Apple)

  2. Masahiro Araki (Kyoto Institute of Technology)

  3. Ron Artstein (USC Institute for Creative Technologies)

  4. rafael banchs (Intapp, Inc)

  5. Parminder Bhatia (Amazon)

  6. Nate Blaylock (Nuance Communications)

  7. Praveen Kumar Bodigutla (Amazon)

  8. Yun-Nung Chen (National Taiwan University)

  9. Paul Crook (Facebook)

  10. Heriberto Cuayahuitl (University of Lincoln)

  11. Ludovic Denoyer (Facebook)

  12. Nina Dethlefs (University of Hull)

  13. Maryam Fazel-Zarandi (Amazon)

  14. Michel Galley (Microsoft)

  15. Kallirroi Georgila (University of Southern California)

  16. Helen Hastie (Heriot-Watt University)

  17. Larry Heck (Samsung Research America)

  18. Matthew Henderson (Google)

  19. Ryuichiro Higashinaka (NTT)

  20. Ravi Jain (Amazon)

  21. Anders Johannsen (Apple)

  22. Filip Jurcicek (Apple)

  23. Chandra Khatri (Uber AI)

  24. Douwe Kiela (Facebook AI Research)

  25. Kazunori Komatani (Osaka University)

  26. Anjishnu Kumar (Amazon)

  27. Sungjin Lee (Microsoft Research)

  28. Fabrice Lefevre (Univ. Avignon)

  29. Oliver Lemon (Heriot-Watt University)

  30. Lihong Li (Google)

  31. Lin Li (Apple)

  32. Lambert Mathias (Amazon)

  33. Angeliki Metallinou (Amazon)

  34. Diarmuid Ó Séaghdha (Apple)

  35. Alexandros Papangelis (Toshiba Research Europe Limited)

  36. Stephen Pulman (Apple)

  37. Giuseppe Riccardi (University of Trento)

  38. Sanjeev Satheesh (Tesla)

  39. Ethan Selfridge (Interactions Corporation)

  40. Amina Shabbeer (Amazon)

  41. Kevin Small (Amazon)

  42. Eddy Su (PolyAI)

  43. Sandeep Subramanian (MILA)

  44. Gyuri Szarvas (Amazon)

  45. Blaise Thomson (Apple)

  46. Gokhan Tur (Google)

  47. Stefan Ultes (Daimler)

  48. Anu Venkatesh (Amazon)

  49. Shawn Wen (PolyAI)

  50. Jason Weston (Facebook AI Research)

  51. Hong Yu (Apple)

  52. Kai Yu (SJTU)

  53. Imed Zitouni (Microsoft)