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

NIPS 2017 - Workshop

 
 

Description

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, Facebook M 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 NIPS, ICML, IJCAI, and others.  Research community challenge tasks are proliferating, including the sixth Dialog Systems Technology Challenge (DSTC6), the Amazon Alexa prize, and the Conversational Intelligence Challenge live competition at NIPS 2017. Now more than ever, it is crucial to promote 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, to share findings from large-scale real-world deployments, and to generate new ideas for future lines of research. This workshop will include invited talks from academia and industry, contributed work, and open discussion.  In these talks, senior technical leaders from many of the most popular conversational services 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













Organizers









Call for Papers

We invite you to submit your contributions here in the area of conversational AI by November 1st 11:59 PM EST in NIPS style with 2-4 pages with maximum of 8 pages. You do not need to anonymize your submissions. Notifications will be sent out by November 21st. Selected papers will be presented through invited talks or posters (max size of 36 x 48in).


Important Dates

Submission:                              1 November 2017 11:59 PM EST (link)

Notification:                             21 November 2017

Camera Ready:                        28 November 2017

Registration:                             see NIPS website

Workshop:                                8 December 2017


Location
Long Beach Convention Center - Grand Ballroom B


Schedule

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

9:10-9:50        Invited Talk: - Satinder Singh (UMich)

9:50-10:10      Accepted Talk: An Ensemble Model with Ranking for Social Dialogue

10:10-10:30    Accepted Talk: A Deep Reinforcement Learning Chatbot

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

11:00-11:40    Invited Talk: Social and Ethical Aspects of Dialogue Systems - Joelle Pineau (McGill/Facebook)
11:40-12:00    Accepted Talk: Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding

12:00-1:30      Lunch Break

1:30-2:10        Invited Talk: Conversational AI at Scale: The Science behind the Alexa Prize - Ashwin Ram (Amazon)

2:10-2:50        Invited Talk: Evolution of Siri - Blaise Thomson (Apple)

2:50-3:05        One Minute Poster Spotlight

3:05-3:30        Coffee Break / Poster Session

3:30-3:50        Invited Talk: Neural Models for Text Generation - Asli Celikyilmaz (Microsoft Research)

3:50-4:10        Invited Talk: Composite task completion bot with Hierarchical RL - Jianfeng Gao (Microsoft Research) [Slides]
4:10-4:30        Invited Talk: Smart reply and Implicit semantics - Matt Henderson (Google)
[Slides]

4:30-4:50        Invited Talk: Conversational Machines: Deep Learning for Goal Oriented Dialogue Systems - Dilek Hakkani-Tur (Google)

4:50-5:20        Poster Session

5:20-6:00        Invited Talk: Quantized Dialog - David Nahamoo (IBM) [Slides]

6:00-6:50        Panel / Open Discussion - All Organizers (submit questions here and enter your info here for Echo Dot raffle)

6:50-7:00        Closing Remarks - Jason Williams (Microsoft Research)


Questions for Panel





















Accepted Papers - Oral

  1. An Ensemble Model with Ranking for Social Dialogue [PDF]
    Ioannis Papaioannou, Amanda Cercas Curry, Jose L. Part, Igor Shalyminov, Xinnuo Xu, Yanchao, Yu Ondrej Dušek, Verena Rieser, and Oliver Lemon

  2. A Deep Reinforcement Learning Chatbot [PDF]
    Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Rajeshwar, Alexandre de Brebisson, Jose M. R. Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau, and Yoshua Bengio

  3. Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding [PDF]
    Bing Liu, and Ian Lane


Accepted Papers - Poster

  1. 1.Personalization in Goal-oriented Dialog [PDF]
    Chaitanya Joshi, Fei Mi, and Boi Faltings

  2. 2.Soc2Seq: Social Embedding meets Conversation Model [PDF]
    Parminder Bhatia, Marsal Gavaldà, and Arash Einolghozati

  3. 3.Rasa: Open Source Language Understanding and Dialogue Management [PDF]
    Tom Bocklisch, Joey Faulkner, Nick Pawlowski Rasa, and Alan Nichol

  4. 4.Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding [PDF]
    Anjishnu Kumar, Arpit Gupta, Julian Chan, Sam Tucker, Bjorn Hoffmeister, and Markus Dreyer

  5. 5.Achieving Fluency and Coherency in Task-oriented Dialog [PDF]
    Rashmi Gangadharaiah, Balakrishnan Narayanaswamy, and Charles Elkan

  6. 6.DialPort: Real-World Data for Academia Spoken Dialog Systems [PDF]
    Tiancheng Zhao, Yulun Du, Kyusong Lee, and Maxine Eskenazi

  7. 7.End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning [PDF]
    Bing Liu, Gokhan Tür, Dilek Hakkani-Tür, Pararth Shah, and Larry Heck

  8. 8.On Evaluating and Comparing Conversational Agents [PDF]
    Anu Venkatesh, Chandra Khatri, Ashwin Ram, Fenfei Guo, Raefer Gabriel, Ashish Nagar, Rohit Prasad, Ming Cheng, Behnam Hedayatnia, Angeliki Metallinou, Rahul Goel, Shaohua Yang, and Anirudh Raju

  9. 9.Topic-based Evaluation for Conversational Bots [PDF]
    Fenfei Guo, Angeliki Metallinou, Chandra Khatri, Anirudh Raju, Anu Venkatesh, and Ashwin Ram

  10. 10.Differentiable lower bound for expected BLEU score [PDF]
    Maksim Kretov, and Vlad Zhukov

  11. 11.Learning Robust Dialog Policies in Noisy Environments [PDF]
    Maryam Fazel-Zarandi, Shang-Wen Li, Jin Cao, Jared Casale, David Whitney, and Alborz Geramifard

  12. 12.Collaboration-based User Simulation for Goal-oriented Dialogue Systems [PDF]
    Devin Didericksen, Oleg Rokhlenko, Kevin Small, and Li Zhou

  13. 13.End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient [PDF]
    Li Zhou, Kevin Small, Oleg Rokhlenko, and Charles Elkan


Program Committee

Alexandros Papangelis (Toshiba Research Europe Limited)

Amina Shabbeer (Amazon)

Chandra Khatri (Amazon)

Ethan Selfridge (Interactions Corporation)

Heriberto Cuayahuitl (University of Lincoln)

Imed Zitouni (Microsoft)

Kallirroi Georgila (USC Institute for Creative Technologies)

Kazunori Komatani (Osaka University)

Kevin Small (Amazon)

Lambert Mathias (Amazon)

Lihong Li (Google)

Masahiro Araki (Kyoto Institute of Technology)

Matthew Henderson (Google)

Michel Galley (Microsoft)

Nate Blaylock (Nuance Communications)

Nina Dethlefs (University of Hull)

Parminder Bhatia (Amazon)

Paul Crook (Microsoft)

Praveen Bodigutla (Amazon)

Rafael E. Banchs (Institute for Info comm Research)

Ravi Jain (Amazon)

Ron Artstein (USC Institute for Creative Technologies)

Rudolf Kadlec (IBM)

Ryuichiro Higashinaka (Nippon Telegraph and Telephone Corporation)

Satoshi Nakaura (Nara Institute of Science and Technology)

Simon Keizer (Heriot-Watt University)

Stefan Ultes (Cambridge University)

Sungjin Lee (Microsoft Research)

Tatsuya Kawahara (Kyoto University)

Yan Yang (Amazon)