DSTC9 Workshop @ AAAI-21
Workshop Information
DSTC9 Workshop will be held at AAAI-21 on February 8-9, 2021 as a two-day virtual event.
The AAAI-21 online registration is available at https://aaai.org/Conferences/AAAI-21/registration/.
Workshop Program - Day 1
February 8 (1 pm to 8:30 pm) in San Francisco & February 9 (5 am to 12:30 pm) in Beijing
* Please note that all times on the following schedule are in Pacific Time (UTC-8).
13:00-13:10 Opening Welcome Remarks, Chulaka Gunasekara [slides]
Track 1: Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access
(Chair: Seokhwan Kim)
13:10-13:45 Track 1 Overview - Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access Track in DSTC9, Seokhwan Kim, Mihail Eric, Behnam Hedayatnia, Karthik Gopalakrishnan, Yang Liu, Chao-Wei Huang, Dilek Hakkani-tur [slides]
13:45-14:10 Towards Generalized Models for Beyond Domain API Task-oriented Dialogue, Haitao Mi, Qiyu Ren, Yinpei Dai, Yifan He, Jian Sun, Yongbin Li, Jing Zheng, Peng Xu
14:10-14:35 Learning to Select External Knowledge with Multi-Scale Negative Sampling, Huang He, Hua Lu, Siqi Bao, Fan Wang, Hua Wu, Zheng-Yu Niu, Haifeng Wang
14:35-15:00 RADGE: Relevance Learning and Generation Evaluating Method for Task-oriented Conversational System, Liang Tang, Qinghua Shang, Kaokao Lv, Zixi Fu, Shijiang Zhang, Chuanming Huang, Zhuo Zhang
15:00-15:20 Break
Track 2: Multi-domain Task-oriented Dialog Challenge II
(Chair: Jinchao Li)
15:20-15:55 Track 2 Overview - Multi-Domain Task Completion Dialog Challenge II at DSTC9, Jinchao Li, Qi Zhu, Lingxiao Luo, Lars Liden, Kaili Huang, Shahin Shayandeh, Run-Ze Liang, Baolin Peng, Zheng Zhang, Swadheen Shukla, Ryuichi Takanobu, Minlie Huang, Jianfeng Gao [slides]
15:55-16:20 Efficient Dialogue State Tracking by Masked Hierarchical Transformer, Min Mao, Jiasheng Liu, Jingyao Zhou, Haipang Wu
16:20-16:45 AuGPT: Dialogue with Pre-trained Language Models and Data Augmentation, Jonáš Kulhánek, Vojtech Hudecek, Tomáš Nekvinda, Ondrej Dusek
16:45-17:10 A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining, Boliang Zhang, Ying Lyu
17:10-17:30 Break
Invited Talk 1
17:30-18:30 Invited Talk - Generation Based Conversational AI, Pascale Fung
Poster Session 1
18:30-19:20 Poster Session: Track 1&2
Relevance Similarity Scorer and Entity Guided Reranking for Knowledge Grounded Dialog System, Hyunkyung Bae, Minwoo Lee, AhHyeon Kim, Hwanhee Lee, Cheongjae Lee, Cheoneum Park, Donghyeon Kim, Kyomin Jung
A Knowledge-Grounded Dialog System Based on Pre-Trained Language Models, Weijie Zhang, Jiaoxuan Chen, Haipang Wu, Sanhui Wan, Gongfeng Li
Dialogue State Enriched Response Generation with Unstructured Knowledge Access, Yi-Hsuan Deng, Ya-Hsin Chang, Yun-Nung Chen
Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog, David Thulke, Nico Daheim, Christian Dugast, Hermann Ney
Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems, Chao-Hong Tan, Xiaoyu Yang, Zi'ou Zheng, Yufei Feng, Tianda Li, Jia-Chen Gu, Quan Liu, Dan Liu, Zhen-Hua Ling, Xiaodan Zhu
End-to-End Document-Grounded Conversation with Encoder-Decoder Pre-Trained Language Model, Jinhyeon Kim, Donghoon Ham, Jeong-Gwan Lee, Kee-Eung Kim
Unstructured Knowledge Access in Task-oriented Dialog Modeling using Language Inference, Knowledge Retrieval and Knowledge-Integrative Response Generation, Mudit Chaudhary, Borislav Dzodzo, Xiaoying Zhang, Jingyan Zhou, Hong Cheng, Wai Lam, Helen Meng, Sida Huang, Tianhua Zhang, Mingzhi Lyu, Jinbo Xing, Chun Hei Lo, Lun Yiu Nie
Simplified Task-Oriented Dialog System using Domain State, Hyunmin Jeon, Gary Geunbae Lee
An Empirical Study of Cross-Lingual Transferability in Generative Dialogue State Tracker, Yen-Ting Lin, Yun-Nung Chen
Panel Discussion
19:30-20:30 Panel Discussion: Role of Research Challenges in shaping Conversational AI Research - Hindsight and Foresight
Moderator: Abhinav Rastogi
Panelists: Chiori Hori, Dilek Hakkani-Tur, Koichiro Yoshino, Rafael E. Banchs
Workshop Program - Day 2
February 9 (1 pm to 7:50 pm) in San Francisco & February 10 (5 am to 11:50 am) in Beijing
* Please note that all times on the following schedule are in Pacific Time (UTC-8).
13:00-13:05 Welcome Remarks, Chulaka Gunasekara [slides]
Track 3: Interactive Evaluation of Dialog
(Chair: Shikib Mehri)
13:05-13:40 Track 3 Overview - Interactive Evaluation of Dialog Track at DSTC9, Shikib Mehri, Yulan Feng, Carla Gordon, Seyed Hossein Alavi, David Traum, Maxine Eskenazi [slides]
13:40-14:05 WeChat AI's Submission for DSTC9 Interactive Dialogue Evaluation Track, Zekang Li, Zongjia Li, Jinchao Zhang, Yang Feng, Jie Zhou
14:05-14:30 A Unified Pre-training Framework for Conversational AI, Siqi Bao, Bingjin Chen, Huang He, Xin Tian, Han Zhou, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Yingzhan Lin
Invited Talk 2
14:30-15:30 Invited Talk - Self Learning for Conversational AI, Gokhan Tur
15:30-15:50 Break
Track 4: SIMMC: Situated Interactive Multi-Modal Conversational AI
(Chairs: Paul Crook, Satwik Kottur, Suengwhan Moon)
15:50-16:25 Track 4 Overview - Situated Interactive Multimodal Conversations (SIMMC) Track at DSTC9, Paul Crook, Satwik Kottur, Suengwhan Moon, Ahmad Beirami, Alborz Geramifard, Eunjoon Cho, Rajen Subba [slides]
16:25-16:50 Joint Generation and Bi-Encoder for Situated Interactive MultiModal Conversations, Xin Huang, Chor Seng Tan, Yan Bin Ng, Wei Shi, Kheng Hui Yeo, Ridong Jiang, Jung Jae Kim
16:50-17:15 A Response Retrieval Approach for Dialogue Using a Multi-Attentive Transformer, Matteo Antonio Senese, Giuseppe Rizzo, Alberto Benincasa, Barbara Caputo
17:15-17:40 TOM : End-to-End Task-Oriented Multimodal Dialog System with GPT-2, Younghoon Jeong, Se Jin Lee, Youngjoong Ko, Jungyun Seo
17:40-18:00 Break
Future DSTC & Closing
18:00-18:40 DSTC10 Challenge Proposals
(Chair: Koichiro Yoshino)
18:40-18:50 Wrap-up Talk, Yun-Nung (Vivian) Chen [slides]
18:50-19:00 Break
Poster Session 2
19:00-19:50 Poster Session: Track 4 & DSTC10 Proposals
Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems, Po-Nien Kung, Tse-Hsuan Yang, Chung-Cheng Chang, Hsin-Kai Hsu, Yu-Jia Liou, Yun-Nung Chen
Improving Multimodal API Prediction via Adding Dialog State and Various Multimodal Gates, Byoungjae Kim, Inkwon Lee, Yeonseok Jeong, Ko Youngjoong, Myoung-Wan Koo, Jungyun Seo
Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning, Jerry Zikun Chen, Shi Yu, Haoran Wang
DSTC10 Proposal: MOD: Internet Meme Incorporated Open-domain Dialog, Zhengcong Fei, Zekang Li, Jinchao Zhang, Yang Feng, Jie Zhou
DSTC10 Proposal: Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, Seokhwan Kim, Yang Liu, Di Jin, Alexandros Papangelis, Behnam Hedayatnia, Karthik Gopalakrishnan, Dilek Hakkani-Tur
DSTC10 Proposal: SIMMC 2.0: Situated Interactive Multimodal Conversational AI, Seungwhan Moon, Satwik Kottur, Paul A. Crook, Ahmad Beirami, Eunjoon Cho, Babak Damavandi, Alborz Geramifard, Rajen Subba
DSTC10 Proposal: Reasoning for Audio Visual Scene-Aware Dialog, Shijie Geng, Peng Gao, Anoop Cherian, Chiori Hori, Tim K. Marks
DSTC10 Proposal: Automatic Evaluation and Moderation of Open-domain Dialogue Systems, Zhang Chen, João Sedoc, Luis Fernando D’Haro, Rafael Banchs, Alexander Rudnicky
Important Dates
Paper submission deadline: Nov 17, 2020
Paper acceptance notification: Dec 3, 2020
Camera-ready submission deadline: Dec 18, 2020
AAAI early registration deadline: Jan 15, 2021
DSTC9 workshop @ AAAI: Feb 8-9, 2021