3rd Conversational AI: “Today's Practice and Tomorrow's Potential”

3rd Conversational AI:
“Today's Practice and Tomorrow's Potential”

NeurIPS 2019 - Workshop

Description

In less than a decade, conversational systems have become commonplace. Every day, millions of people use natural-language interfaces such as Siri, the Google Assistant, 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. Such movement has not been unnoticed by major publications. This year in collaboration with AAAI community, the AI magazine will have a special issue on conversational AI. Moreover, 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 two successful NeurIPS workshops:
2017: 9 invited talks, 26 submissions, 3 oral papers, 13 accepted papers, 37 reviewers

2018: 4 invited talks, 42 submission, 6 oral papers, 23 accepted papers, 58 reviewers,

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, understand well-founded methods, share findings from large-scale real-world deployments, and 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. We will end the day with an open discussion, including a panel consisting of academic and industrial researchers.

Invited Speakers

❖Y-Lan Boureau (Facebook)
❖Ryuchiro Higashinaka (NTT)
❖Alan Ritter (Ohio State University)
❖Gabriel Skantze (KTH, Furhat Robotics)
❖David Traum (USC)
❖Zhou Yu (UC Davis): *Unable to deliver her talk due to visa issues

Chairs:

Organizers:

Call for Papers

We invite you to submit your novel contributions (submission page) in the area of conversational AI 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). Selected papers will be presented through invited talks or posters. Maximum allowed size of posters is 36 x 48 inch (91 x 122 cm). Posters should be on light weight paper and not laminated. Submitting papers that are under review by other venues are ok. However, please avoid submitting already peer-reviewed and published work. 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 (alborz dot geramifard at gmail dot com; jdw at alumni dot princeton dot edu).

Two phase submission process

This year, we will have two submission phases due to limitation for allocating tickets to authors. We advise all workshop attendees to enter their names for the NeurIPS lottery here.

Phase 1 (Early Submission): Please follow the early submission, only if you did not win a ticket in the NeurIPS lottery. We will notify accepted authors by October 1st and provide tickets to the author presenting the paper.

Submission: 21st September 2019 11:59 PM EST (link)

Notification: 1st October 2019

Phase 2 (Regular Submission): If you already acquired the NeurIPS ticket, please follow the regular submission process below.

Submission: 1st October 2019 11:59 PM EST (link)

Notification: 1st November 2019

Shared dates for both phases:

Camera Ready: 14th November 2019

Registration Start: 6th September 2019

Workshop: 14th December 2019 (Saturday - Second day of workshops)

Location
Vancouver Convention Center, CANADA

Schedule

[Session 1 Video Link]

8:45-8:55 Opening [Video]

8:55-9:25 Invited Talk - Alan Ritter [Video]

9:25-9:40 Contributed talk 1: Attention over Parameters for Dialogue Systems [Video]

9:40-9:55 Poster - Lightning round

9:55-10:40 Coffee Break / Poster Session

[Session 2 Video Link]

10:40-11:10 Invited Talk - Ryuchiro Higashinaka [Video]

11:10-11:25    Contributed talk 2: Persona-aware Dialogue Generation with Enriched Profile
11:25-11:40    Contributed talk 3: HSCJN: A Holistic Semantic Constraint Joint Network for Diverse Response Generation [Video]
11:40-11:55    Contributed talk 4: Hierarchical Reinforcement Learning for Open-Domain Dialog [Video]

11:55-1:45 Lunch Break

[Session 3 Video Link]

1:45-2:15 Invited Talk - David Traum

2:15-2:45 Invited Talk - Y-Lan Boureau [Video]

2:45-3:00 Contributed talk 5: Domain Transfer in Dialogue Systems without Turn-Level Supervision [Video]

3:00-3:15 Contributed talk 6: Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings [Video]

3:15-3:30 Contributed talk 7: Bayes-Adaptive Monte-Carlo Planning and Learning for Goal-Oriented Dialogues [Video]

3:30-4:15 Coffee Break / Poster Session

[Session 4 Video Link]

4:15-4:45 Invited Talk - Gabriel Skantze [Video]
4:45-5:00 Contributed talk 8: Recurrent Chunking Mechanisms for Conversational Machine Reading Comprehension [Video]

5:00-5:50 Panel / Open Discussion - All invited speakers (submit questions here)

5:50-6:00 Closing Remarks

Questions for Panel

Best Paper Award

Accepted Papers - Talk

❖Bayes-Adaptive Monte-Carlo Planning and Learning for Goal-Oriented Dialogues [PDF]
Jang, Youngsoo; Lee, Jongmin; Kim, Kee-Eung
❖Domain Transfer in Dialogue Systems without Turn-Level Supervision [PDF]
Bingel, Joachim; Petrén Bach Hansen, Victor; Gonzalez, Ana V; Budzianowski, Paweł; Augenstein, Isabelle; Søgaard, Anders
❖Persona-aware Dialogue Generation with Enriched Profile [PDF]
Zheng, Yinhe; Chen, Guanyi; Huang, Minlie; Liu, Song; Zhu, Xuan
❖[Best Paper] Attention over Parameters for Dialogue Systems [PDF]
Madotto, Andrea; Lin, Zhaojiang; Wu, Chien-Sheng; Shin, Jamin; Fung, Pascale
❖Hierarchical Reinforcement Learning for Open-Domain Dialog [PDF]
Saleh, Abdelrhman; Jaques, Natasha; Ghandeharioun, Asma; Shen, Judy Hanwen; Picard, Rosalind
❖Recurrent Chunking Mechanisms for Conversational Machine Reading Comprehension [PDF]
Gong, Hongyu; Shen, Yelong; Yu, Dian; Chen, Jianshu; Yu, Dong
❖HSCJN: A Holistic Semantic Constraint Joint Network for Diverse Response Generation [PDF]
Wang, Yiru; Si, Pengda; Lei, Zeyang; Xun, Guangxu; Yang, Yujiu
❖Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings [PDF]
Mendez, Jorge A; Geramifard, Alborz; Ghavamzadeh, Mohammad; Liu, Bing

Accepted Papers - Poster

1.Multi-Turn Beam Search for Neural Dialogue Modeling [PDF]
Kulikov, Ilia*; Lee, Jason; Cho, Kyunghyun
2.Just Ask:An Interactive Learning Framework for Vision and Language Navigation [PDF]
Chi, Ta-Chung*; Shen, Minmin; Eric, Mihail; Kim, Seokhwan; Hakkani-tur, Dilek
3.Improving Robustness of Task Oriented Dialog Systems [PDF]
Einolghozati, Arash*; Gupta, Sonal; Mohit, Mrinal; Shah, Rushin
4.Hierarchical Tensor Fusion Network for Deception Handling Negotiation Dialog Model [PDF]
Nguyen, The Tung*; Yoshino, Koichiro; Sakti, Sakriani; Nakaura, Satoshi
5.Conversational QA for FAQs [PDF]
Campos, Jon Ander*; Agirre, Eneko; Soroa, Aitor; Otegi, Arantxa; Deriu, Jan; Cieliebak, Mark
6.Dialogue Model and Response Generation for Emotion Improvement Elicitation [PDF]
Lubis, Nurul*; Sakti, Sakriani; Yoshino, Koichiro; Nakaura, Satoshi
7.ACUTE-EVAL: Improved dialogue evaluation with optimized questions and multi-turn comparisons [PDF]
Li, Margaret*; Weston, Jason; Roller, Stephen;
8.MA-DST: Multi-Attention-Based Scalable Dialog State Tracking [PDF]
Kumar, Adarsh*; Ku, Peter; Goyal, Anuj Kumar; Metallinou, Angeliki; Hakkani-tur, Dilek
9.Aging Memories Generate More Fluent Dialogue Responses with Memory Augmented Neural Networks [PDF]
Florez, Omar U*; Muller, Erik
10.Learning to Control Latent Representations \or Few-Shot Learning of Named Entities [PDF]
Florez, Omar U*; Muller, Erik
11.Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning [PDF]
Neelakantan, Arvind*; Narang, Sharan; Yavuz, Semih
12.Retrieval-based Goal-Oriented Dialogue Generation [PDF]
Gonzalez, Ana V*; Augenstein, Isabelle; Søgaard, Anders
13.Investigation of Error Simulation Techniques for Learning Dialog Policies for Conversational Error Recovery [PDF]
Fazel-Zarandi, Maryam*; Wang, Longshaokan; Tiwari, Aditya; Matsoukas, Spyros
14.Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog [PDF]
Jaques, Natasha*; Ghandeharioun, Asma; Shen, Judy Hanwen; Ferguson, Craig; Lapedriza Garcia, Agata; Jones, Noah; Gu, Shixiang; Picard, Rosalind
15.Incorporating rules into end-to-end dialog systems [PDF]
Razumovskaia, Evgeniia*; Eskenazi, Maxine
16.Learning Conversational Web Interfaces [PDF]
Gur, Izzeddin*; Yan, Xifeng
17.Towards Personalized Dialog Policies for Conversational Skill Discovery [PDF]
Fazel-Zarandi, Maryam*; Biswas, Sampat; Summers, Ryan; Elmalt, Ahmed; McCraw, Andy; McPhilips, Michael; Peach, John
18.The Eighth Dialog System Technology Challenge [PDF]
Kim, Seokhwan*; Galley, Michel; Gunasekara, Chulaka; Lee, Sungjin; Atkinson, Adam; Peng, Baolin; Schulz, Hannes; Gao, Jianfeng; Li, Jinchao; Adada, Mahmoud; Huang, Minlie; Lastras, Luis A.; Kummerfeld, Jonathan K; Lasecki, Walter; Hori, Chiori; Cherian, Anoop; Marks, Tim K; Rastogi, Abhinav; Zang, Xiaoxue; Sunkara, Srinivas; Gupta, Raghav
19.Multi-domain Conversation Quality Evaluaiton via User Satisfaction Estimation [PDF]
Bodigutla, Praveen Kumar*; Matsoukas, Spyros; Polymenakos, Lazaros
20.Paper details to be posted at a later date, at author’s request
<Authors>
21.TAM: Using trainable-action-mask to improve sample-efficiency in reinforcement learning for dialogue systems [PDF]
Wu, Yen-Chen*
22.Domain-Specific Question Answering at Scale for Conversational Systems [PDF]
Semnani, Sina; Pandey, Madhulima ; Pandey, Manish*