Conversational challenge announced! See convai.io website for details.
The 5nd International Workshop on Search-Oriented Conversational AI (SCAI)
Online 🌐, November 19, 2020 (co-located with EMNLP 2020).
Click here to go to the SCAI main page.
More and more information is found and consumed in a conversational form rather than using traditional search engines. Chatbots, personal assistants in our phones and eyes-free devices are being used increasingly more for different purposes, including information retrieval and exploration. On the other side, information retrieval empowers dialogue systems to answer questions and to get context for assisting the user in her tasks. With the recent success of deep learning in different areas of natural language processing, this appears to be the right foundation to power search conversationalization. Yet, we believe more can be done for theory and practice of conversation-based search and search-based dialogues.
This workshop aims to bring together researchers from the NLP, Machine Learning, and IR communities to lay the ground for search-oriented conversational AI and establish future directions and collaborations.
The 1st edition of the workshop was co-located with International Conference on the Theory of Information Retrieval (ICTIR 2017).
The 2nd edition of the workshop was co-located with the Conference on Emperical Methods in Natural Language Processing (EMNLP 2018).
The 3rd edition (special half-day edition) of the workshop was co-located with The Web Conference 2019 (TheWebConf 2019).
The 4th edition of the workshop was co-located with the International Joint Conoference on Artificial Intelligence (IJCAI 2019).
- Surfacing search results or other information in form of a dialogue how to present information coming from search in a form of a dialogue how ensure smooth transition between dialog turns which model to use for dialog-state tracking
- Conversationalization of the information: analyzing syntactic structure of the text and modifying it to be more suitable in a conversational setting
- Text summarization for dialog
- Evaluation of Search-Oriented Conversational AI — From Conversational AI to Personal Assistants
- The role of personalization for Conversational AI and for its evaluation
- Deep Learning for Conversational AI
- (Deep) Reinforcement Learning for Conversational AI
- Voice as Input (when we consider not only text input, but also voice interactions with the agent — how will it affect existing models?)
- See the main conference's rules: https://2020.emnlp.org/call-for-papers
- Submission URL: https://www.softconf.com/emnlp2020/scai2020/
- Given that the paper submission deadline and notification date were adjusted due to COVID-19, an exception was made to allow double submissions to both EMNLP and its workshops. Note, that the reviews from the main conference will be forwarded to the workshop's Program Committee.
- Submission deadline:
August 15, 2020August 30, 2020 - Retraction deadline for papers accepted to for the main EMNLP conference: September 15, 2020
- Notification of acceptance:
September 29, 2020October 2, 2020 - Camera-ready deadline:
October 10, 2020 - Workshop: November 19, 2020
- Jeff Dalton, University of Glasgow, Glasgow
- Aleksandr Chuklin, Google Research, Zürich
- Julia Kiseleva, Microsoft Research & AI, Seattle
- Mikhail Burtsev, MIPT, Moscow
- Invited Speakers and Oral Presentation
- Panel Discussion.
- Breakout Session to plan a roadmap for Conversational AI
- Poster Session
- Y-Lan Boureau, Facebook AI Research
- Title: Better-behaved Conversational Agents
- [recording]
- Thomas Wolf, Hugging Face
- Title: Transfer Learning and tools for Conversational Agents
- [recording]
- Verena Rieser, Heriot Watt University
- Title: Response Generation and Retrieval for Multimodal Conversational AI
- [recording]
- Ivan Vulic, PolyAI
- Title: Data-Efficient Natural Language Understanding for Task-Oriented Dialogue
- [recording]
- Sungjin Lee, Amazon
- Title: Towards Self-Learning for Large Scale Conversational Agents
- [recording]
- Jason Weston, Facebook AI Research
- Title: BlenderBot, Knowledge and Search
- [recording]
- Jian-Yun Nie, Université de Montréal
- Title: Smooth Training for �Open-Domain Question Answering
- [recording]
- Slice-Aware Neural Ranking by Gustavo Penha, Claudia Hauff [paper page] [recording] [rocket.chat: #paper-scai-1]
- A Wrong Answer or a Wrong Question? An Intricate Relationship between Question Reformulation and Answer Selection in Conversational Question Answering by Svitlana Vakulenko, Shayne Longpre, Zhucheng Tu, Raviteja Anantha [paper page] [recording] [rocket.chat: #paper-scai-paper2]
- Multi-Task Learning using Dynamic Task Weighting for Conversational Question Answering by Sarawoot Kongyoung, Craig Macdonald, Iadh Ounis [paper page] [recording] [rocket.chat: #paper-scai-3]
- Semantically Driven Sentence Fusion: Modeling and Evaluation by Eyal Ben-David, Orgad Keller, Eric Malmi, Idan Szpektor, Roi Reichart [paper page] [recording] [rocket.chat #paper-scai-paper3]
- Toward Stance-based Personas for Opinionated Dialogues by Thomas Scialom, Serra Sinem Tekiroglu, Jacopo Staiano, Marco Guerini [paper page] [recording] [rocket.chat #paper-scai-2041]
- Filtering before Iteratively Referring for Knowledge-Grounded Response Selection in Retrieval-Based Chatbots by Jia-Chen Gu, Zhen-Hua Ling, Quan Liu, Zhigang Chen, Xiaodan Zhu [paper page] [recording] [rocket.chat #paper-scai-1175]
- TSDG: Content-aware Neural Response Generation with Two-stage Decoding Process by Junsheng Kong, Zhicheng Zhong, Yi Cai, Xin Wu, Da Ren [paper page] [recording] [rocket.chat #paper-scai-1735]
- ConveRT: Efficient and Accurate Conversational Representations from Transformers by Matthew Henderson, Iñigo Casanueva, Nikola Mrkšić, Pei-Hao Su, Tsung-Hsien Wen, Ivan Vulić [paper page] [recording] [rocket.chat #paper-scai-1761-ws4]
- Learning Improvised Chatbots from Adversarial Modifications of Natural Language Feedback by Makesh Narsimhan Sreedhar, Kun Ni, Siva Reddy [paper page] [recording] [rocket.chat #paper-scai-1947]
- Joint Turn and Dialogue level User Satisfaction Estimation on Multi-Domain Conversations by Praveen Kumar Bodigutla, Aditya Tiwari, Josep Vallas Vargas, Lazaros Polymenakos, Spyros Matsoukas [paper page] [recording] [rocket.chat #paper-scai-2889]
- Making Information Seeking Easier: An Improved Pipeline for Conversational Search by Vaibhav Kumar, Jamie Callan [paper page] [recording] [rocket.chat #paper-scai-2957]
- SMRT Chatbots: Improving Non-Task-Oriented Dialog with Simulated Multi-Reference Training by Huda Khayrallah, João Sedoc [paper page] [recording] [rocket.chat #paper-scai-3361]
- Clarifying Questions in Conversations with Augmented Syntax Features and Side Information - TAL ML Team's Solution for ConvAI3 Challenge by Hang Li, Tianqiao Liu, Yu Kang, Guowei Xu, Wenbiao Ding, Zitao Liu [recording]
- Clarifying Questions for Conversational Search Systems: Team Soda’s Solution for the ClariQ Challenge by Jian Wang, Wenjie Li [recording]
- A Clarifying Question Selection System from NTES_ALONG in Convai3 Challenge by Wenjie Ou, Yue Lin [recording]
See convai.io for more information about the challenge.
Please check the EMNLP website for the latest schedule updates, including the schedle in your timezone.
Below is a preliminary schedule that is subject to change without prior warning.
<iframe src="https://docs.google.com/spreadsheets/d/e/2PACX-1vTim2zwWcRrrZpQAzXA-l2PfiONt332rMhndatIf7ZcntbFzECXbbcqSaYHz465gJwbbgfbiKOgfJXk/pubhtml?gid=2035305167&single=true&widget=true&headers=false" width="1200" height="600" frameborder="1" marginheight="0" marginwidth="0"></iframe>