| CARVIEW |
Overview
Welcome to 1st DialDoc Workshop at ACL-IJCNLP 2021!
Goal-oriented conversational systems can unlock a vast amount of information in the associated documents, in which written and visual content dominate the way that individuals and organizations choose to present their interests and knowledge to the world. We posit that one scalable way to create personalized conversational systems is to have them arise directly from such content. There are significant individual research threads that show promises in handling heterogeneous knowledge embedded in the documents, including (1) unstructured content such as text passages (CoQA, QuAC, ShARC, Doc2Dial ); (2) semi-structured content such as tables or lists (SQA, HybridQA ); (3) multimedia such as images and videos with associated textual descriptions (RecipeQA, Clue, MultiModalQA); (4) or structured data specified by schema such as RDFa or Microdata in the webpages. The purpose of this workshop on Document-grounded Dialogue and Conversational QA is to invite researchers to bring their individual perspectives on the subject, and to advance the field in joint effort by providing a shared task and competition.
Invited Speakers
![]() |
![]() |
![]() |
![]() |
| Jonathan Berant Tel-Aviv University |
Danqi Chen Princeton University |
Dilek Hakkani-Tur
Amazon Alexa AI) . |
Verena Rieser Heriot-Watt University |
![]() |
![]() |
![]() |
|
| Jason Weston Facebook AI Research |
William Wang University of California, Santa Barbara |
Scott (Wen-tau) Yih Facebook AI Research |
Program
August 5, 2021, Thursday, 8:00 - 17:40 EDT
- 08:00–08:05 | Opening Remarks
- 08:05–08:40 | Invited Talk 1: Jonathan Berant - Exposing and Covering Language Model Blind Spots by Generating Data from Structured Representations
- 08:40–09:15 | Invited Talk 2: Verena Rieser - Grounded Neural Generation
- 09:15–10:05 | Paper Lightning Talk I
SeqDialN: Sequential Visual Dialog Network in Joint Visual-Linguistic Representation Space
Liu Yang | Fanqi Meng | Xiao Liu | Ming-Kuang Daniel Wu | Vicent Ying | James XuA Template-guided Hybrid Pointer Network for Knowledge-based Task-oriented Dialogue Systems
Dingmin Wang | Ziyao Chen | Wanwei He | Li Zhong | Yunzhe Tao | Min YangCombining Open Domain Question Answering with a Task-Oriented Dialog System
Jan Nehring | Nils Feldhus | Harleen Kaur | Akhyar AhmedQ2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering
Or Honovich | Leshem Choshen | Roee Aharoni | Ella Neeman | Idan Szpektor | Omri AbendSummary-Oriented Question Generation for Informational Queries
Xusen Yin | Li Zhou | Kevin Small | Jonathan MayHyKnow: End to end Task oriented Dialog Modeling with Hybrid Knowledge Management
Silin Gao | Ryuichi Takanobu 1 | Wei Peng | Qun Liu | Minlie HuangDialogue Graph Modeling for Conversational Machine Reading
SiruOuyang | ZhuoshengZhang | Hai ZhaoPhrase-Level Action Reinforcement Learning for Neural Dialog Response Generation
Takato Yamazaki | Akiko Aizawa - 10:05–10:30 | Break
- 10:30–11:05 | Invited Talk 3: Jason Weston - Towards Knowledgeable Open-Domain Dialogue Agents
- 11:05-11:30 | Shared Task Results
- 11:30-12:30 | Poster Session I
- 12:30-13:30 | Lunch break
- 13:30–14:05 | Invited Talk 4: Danqi Chen - Learning Representations for Dense Retrieval
- 14:05–14:55 | Paper Lightning Talk II
WeaSuLπ: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue
Anant KhandelwalBuilding Goal-oriented Document-grounded Dialogue Systems
Xi Chen | Faner Lin | Yeju Zhou | Kaixin Ma | Jonathan Francis | Eric Nyberg | Alessandro OltramariAgenda Pushing in Email to Thwart Phishing
Hyundong Cho | Genevieve Bartlett | Marjorie FreedmanCan I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling
Di Jin | Seokhwan Kim | Dilek Hakkani-TurKnowledge-Grounded Dialogue Generation with Term-level De-noising
Wen Zheng | Natasa Milic Frayling | Ke ZhouSummary Grounded Conversation Generation
Chulaka Gunasekara | Guy Feigenblat | Benjamin Sznajder | Sachindra Joshi | David Konopnicki - 14:55–15:30 | Invited Talk 5: Dilek Hakkani-Tur - Integrating Unstructured Knowledge in Responses of Conversational Systems
- 15:30–16:30 | Poster Session II
- 16:30-17:05 | Invited Talk 6: William Wang Yang - Question Answering over Text and Tables
- 17:05–17:40 | Invited Talk 7: Scott (Wen-tau) Yih - Conversational Question Answering






