The 2nd International Workshop on Search-Oriented Conversational AI (SCAI)
at EMNLP 2018, Brussels, Belgium 🇧🇪, October 31.
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).
- 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?)
- Up to six pages of content in the ACL format, plus unlimited pages for references.
- Submission URL: https://www.softconf.com/emnlp2018/scai18/
- EMNLP's Multiple Submission Policy applies: should a conceptually similar version of the same paper be accepted elsewhere, the authors would need to decide which submission they want to keep and withdraw the other one.
Submission: August 3Notification: August 22Camera-ready version: August 31- Workshop: October 31
- Aleksandr Chuklin, Google AI, Zürich
- Jeff Dalton, University of Glasgow, Glasgow
- Julia Kiseleva, University of Amsterdam, Microsoft Research & AI, Seattle
- Alexey Borisov, Yandex & University of Amsterdam, Moscow
- Mikhail Burtsev, MIPT, Moscow
- Joelle Pineau, McGill University
- Michel Galley, Microsoft Research
- Maarten de Rijke, University of Amsterdam
- Damiano Spina, RMIT University
- Igor Shalyminov, Heriot-Watt University
- Jaap Kamps, University of Amsterdam
- Tom Kenter, Google London
- Valentin Malykh, MIPT
- Evgeny Kharitonov, Facebook Paris
- Guillermo Garrido, Google Zürich
- Scott Roy, Google Mountain View
- Sascha Rothe, Google Zürich
- Invited Speakers and Oral Presentation
- Panel Discussion. You can send your suggestions.
- Breakout Session to plan a roadmap for Conversational AI
- Poster Session
- Milica Gasic, University of Cambridge
- Title: Towards natural conversation with machines using deep learning
- Abstract: Deep learning has made a revolution in machine learning, natural language processing and computer vision. In this talk, I will explain how deep learning can help solve some of the problems that dialogue modelling is facing. These include: scalable belief tracking, policy optimisation for large action spaces, and data-driven user modelling. I will also briefly advertise an initiative of the Cambridge Dialogue Systems Group to address the problem of evaluation of dialogue systems.
- slides
- Mari Ostendorf, University of Washington
- Title: Understanding the User in Socialbot Conversations
- Abstract: Much past research on human-computer dialog has addressed task-oriented scenarios, but there is growing interest in building systems with social interaction capabilities, from companionship chitchat to information and opinion exchange. For systems that emphasize social interaction (e.g. a socialbot), user modeling can be especially important -- people have different tastes in conversation topics as well as different interaction styles. This talk looks at the user in spoken interactions enabled by Sounding Board, a socialbot developed for the 2017 Amazon Alexa Prize competition, which enabled collection of millions of conversations with real users. We describe mechanisms for characterizing user variation and first steps towards predicting conversational preferences.
- Jason Weston, Facebook
- Title: Wizard of Wikipedia: Knowledge-Powered Conversational Agents
- Abstract: In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date. The most popular sequence to sequence models typically “generate and hope” generic utterances that can be memorized in the weights of the model when mapping from input utterance(s) to output, rather than employing recalled knowledge as context. Use of knowledge has so far proved difficult, in part because of the lack of a supervised learning benchmark task which exhibits knowledgeable open dialogue with clear grounding. To that end we collect and release a large dataset with conversations directly grounded with knowledge retrieved from Wikipedia. We then design architectures capable of retrieving knowledge, reading and conditioning on it, and finally generating natural responses. Our best performing dialogue models are able to conduct knowledgeable discussions on open-domain topics as evaluated by automatic metrics and human evaluations, while our new benchmark allows for measuring further improvements in this important research direction. This is joint work with Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan and Michael Auli (joint first authors).
- slides
- Yun-Nung (Vivian) Chen, National Taiwan University
- Title: Towards Open-Domain Conversational AI
- Abstract: Interacting with machines via natural language has been an emerging trend. The goal of developing open-domain dialogue systems that not only emulate human conversation but fulfill complex tasks, such as travel planning, seemed elusive. Recent advances in deep learning enabled new research frontiers for end-to-end conversational systems. This talk will review the research work about deep learning and reinforcement learning technologies that have been developed for two types of conversational agents. First is a task-oriented dialogue system that can help users accomplish tasks, ranging from meeting scheduling to vacation planning. Second is a social bot that can converse seamlessly and appropriately with humans. This talk will conclude with the advanced work that attempted to develop open-domain neural dialogue systems by combining the strengths of both types of agents.
- slides
- Mithun Das Gupta, Microsoft
- Title: Dialogues, Speech and Vision: Communication to make AI more human
- Abstract: Conversational AI such as Alexa, Siri, Google Home and Cortana are now strongly part of people lives. Numerous non-task oriented agents are also gaining importance such as Xiaoice and Ruuh. We will talk about the recent efforts going on to make these agents more human. We take a three pronged approach, dialogue, speech and vision to extend the humanness of these agents. In this talk we will touch upon some of the multi-faceted work going on in Microsoft IDC Hyderabad to attack some of these subfields which make AI more human.
- slides
- 09:00–09:10 Introduction
Session 1
- 09:10–09:50 Keynote 1: Yun-Nung (Vivian) Chen (slides)
- 09:50–10:30 Keynote 2: Jason Weston (slides)
- 10:30–11:00 Break
Session 2
- 11:15–11:55 Keynote 3: Mithun Das Gupta (slides)
- 11:55–12:45 Paper presentations (10 min + 2 min Q/A)
- Neural Response Ranking for Social Conversation: A Data-Efficient Approach. Igor Shalyminov, Ondřej Dušek and Oliver Lemon (slides)
- Autonomous Sub-domain Modeling for Dialogue Policy with Hierarchical Deep Reinforcement Learning. Giovanni Yoko Kristianto, Huiwen Zhang, Bin Tong, Makoto Iwayama and Yoshiyuki Kobayashi (slides)
- Building Dialogue Structure from Discourse Tree of a Question. Boris Galitsky and Dmitry Ilvovsky (slides)
- A Methodology for Evaluating Interaction Strategies of Task-Oriented Conversational. Marco Guerini, Sara Falcone and Bernardo Magnini
- 12:45–14:00 Lunch break
Session 3
- 14:00–14:40 Keynote 4: Milica Gašić (slides)
- 14:40–15:05 Paper presentations (10 min + 2 min Q/A)
- 15:05–16:00 Poster session
- 15:30–16:00 Break (overlapping with the poster session)
Session 4
- 16:00–17:00 Panel discussion
- Milica Gašić, University of Cambridge
- Antoine Bordes, Facebook AI Research
- Jason Weston, Facebook
- Bill Dolan, Microsoft Research
- 17:00–17:40 Keynote 5: Mari Ostendorf
- 17:40–17:50 Closing
Posters
- Curriculum Learning Based on Reward Sparseness for Deep Reinforcement Learning of Task Completion Dialogue Management. Atsushi Saito
- Data Augmentation for Neural Online Chats Response Selection. Wenchao Du and Alan Black
- A Knowledge-Grounded Multimodal Search-Based Conversational Agent. Shubham Agarwal, Ondřej Dušek, Ioannis Konstas and Verena Rieser
- Embedding Individual Table Columns for Resilient SQL Chatbots. Bojan Petrovski, Ignacio Aguado, Andreea Hossmann, Michael Baeriswyl and Claudiu Musat
- Exploring Named Entity Recognition As an Auxiliary Task for Slot Filling in Conversational Language Understanding. Samuel Louvan and Bernardo Magnini
- Why are Sequence-to-Sequence Models So Dull? Understanding the Low-Diversity Problem of Chatbots. Shaojie Jiang and Maarten de Rijke
- Retrieve and Refine: Improved Sequence Generation Models For Dialogue. Jason Weston, Emily Dinan and Alexander Miller
