| 08:30-09:00 | Registration | |
| Opening | ||
|---|---|---|
| 09:00-09:10 | Welcome Remarks from DSTC Steering Committee | Jason Williams (Microsoft Research) |
| 09:10-09:15 | DSTC6 Overview | Seokhwan Kim (Adobe Research) |
| Track 1: End-to-End Goal Oriented Dialog Learning | ||
| 09:15-09:35 | Track Overview | Julien Perez (Naver Labs Europe) |
| 09:35-09:55 | Extended Hybrid Code Networks for DSTC6 FAIR Dialog Dataset | Jiyeon Ham, Soohyun Lim, Kee-Eung Kim |
| 09:55-10:15 | Modeling Conversations to Learn Responding Policies of E2E Task-oriented Dialog System | Ziwei Bai, Bo Yu, Guangyu Chen, Baoxun Wang, Zhuoran Wang |
| 10:15-10:30 | Coffee break | |
| Invited Talk 1 | ||
| 10:30-11:10 | Dialogue as multitask learning and question answering | Dr. Richard Socher (Salesforce) |
| 11:10-11:20 | Q&A | |
| Track 2: End-to-End Conversation Modeling | ||
| 11:20-11:40 | Track Overview | Chiori Hori (MERL) |
| 11:40-12:00 | The MSR-NLP System at Dialog System Technology Challenges 6 | Michel Galley, Chris Brockett, Bill Dolan, Jianfeng Gao |
| Invited Talk 2 | ||
| 12:00-12:40 | Visual Dialog: Towards AI agents that can see, talk, and act | Dr. Dhruv Batra (Georia Tech/FAIR) |
| 12:40-12:50 | Q&A | |
| 12:50-14:10 | Lunch Break & Sponsor Talks | |
| Track 3: Dialog Breakdown Detection | ||
| 14:10-14:30 | Track Overview | Ryuichiro Higashinaka (NTT) |
| 14:30-14:50 | Dialogue Breakdown Detection based on Estimating Appropriateness of Topic Transition | Hiroaki Sugiyama |
| 14:50-15:10 | RSL17BD at DBDC3: Computing Utterance Similarities based on Term Frequency and Word Embedding Vectors | Sosuke Kato , Tetsuya Sakai |
| 15:10-15:30 | How Generic Can Dialogue Breakdown Detection Be? The KTH entry to DBDC3 | Jose Lopes |
| 15:30-15:45 | Coffee Break & Flash Talk by Poster Presenters | |
| Poster Session | ||
| 15:45-17:15 | Poster Presentations: | |
| End-to-End Recurrent Entity Network for Entity-Value Independent Goal-Oriented Dialog Learning Chien-Sheng Wu, Andrea Madotto, Genta Winata, Pascale Fung | ||
| Learning Dynamic Memory Network with Two Views Chang-Uk Shin, Jeong-Won Cha | ||
| End-to-end memory networks with word-abstraction and contextual-numbering for goal oriented task Asuka Sakai, Hongjie Shi, Takashi Ushio, Mitsuru Endo | ||
| End-to-End Goal Oriented Dialog Learning Based On Memory Network Byoungjae Kim, KyungTae Chung, Jeongpil Lee, Jungyun Seo, Myoung-Wan Koo | ||
| Quantized-Dialog Language Model for Goal-Oriented Conversational Systems Chulaka Gunasekara, David Namahoo, Lazaros Polymenakos, Jatin Ganhotra, Kshitij Fadnis | ||
| A Knowledge Enhanced Generative Conversational Service Agent Yinong Long, Jianan Wang, Zhen Xu, Zongsheng Wang, Baoxun Wang, Zhuoran Wang | ||
| Comparative Analysis of Word Embedding Methods for DSTC6 End-to-End Conversation Modeling Track Bairong Zhuang, Wenbo Wang, Zhiyu Li, Chonghui Zheng, Takahiro Shinozaki | ||
| Sequence Adversarial Training and Minimum Bayes Risk Decoding for End-to-end Neural Conversation Models Wen Wang, Yusuke Koji, Bret Harsham, Takaaki Hori, John Hershey | ||
| End-to-end Character-Level Dialogue Breakdown Detection with External Memory Models Atsushi Saito, Taichi Iki | ||
| Dialogue Breakdown Detection using Hierarchical Bi-Directional LSTMs Zeying Xie, Guang Ling | ||
| Attention-based Dialog Embedding for Dialog Breakdown Detection Chanyoung Park, Kyungduk Kim, Songkuk Kim | ||
| Dialogue Breakdown Detection Considering Annotation Biases Junya Takayamy, Eriko Nomoto, Yuki Arase | ||
| Closing | ||
| 17:15-17:55 | DSTC6 Review/DSTC7 Track Proposals | Koichiro Yoshino (NAIST) |
| 17:55-18:00 | Wrap-up Talk | Chiori Hori (MERL) |
| Optional Excursion | ||
|---|---|---|
| 13:30-16:30 | Lab tour at University of Southern California (optional) | |
For lab tour participants: Please gather at,
12015 Waterfront Drive Playa Vista, CA 90094-2536
by 13:15. We don't provide any transportation, please share ride service.
The DSTC6 workshop is sponsored by Adobe Research, Mitsubishi Electric Research Laboratories, and Nara Institute of Science and Technology, and endorsed by International Speech Communication Association (ISCA). The workshop proceedings will be available in the ISCA archive.
 |
 |
 |
|