- 8/8/2022: Video recordings of all sessions are now available (see below).
This workshop is intended as a discussion platform on Conversational AI for intelligent information access, bringing together researchers and practitioners across natural language processing, information retrieval, machine learning and human-computer interaction fields. Among other topics, we will discuss design, evaluation and human factors in relation to automating information-seeking dialogues. The workshop will also feature a shared task on Conversational Question Answering.
SCAI 2022 is a 7th iteration of SCAI. This year, the workshop focuses on the discussion between researchers from different fields. It is therefore organized as a strictly non-archival venue, as an opportunity to present papers accepted to other venues in an interdisciplinary meeting specifically focused on search-based conversational AI. SCAI 2022 is a hybrid workshop at SIGIR 2022, taking place on 15 July (full day).
SCAI is already an established venue with a long-standing tradition of building bridges and integrating expertise from diverse research communities. It was previously organised in the context of ICTIR 2017, EMNLP 2018, TheWebConf 2019, IJCAI 2019 and EMNLP 2020, and as a separate online event in 2021.
SCAI 2022 Program
Session 1: Evaluation (9:00-10:30 CEST) [video]
- Jing Wei (University of Melbourne): What Could Possibly Go Wrong When Interacting with Proactive Smart Speakers? A Case Study Using an ESM Application CHI 2022
- Guglielmo Faggioli (University of Padova): A Dependency-Aware Utterances Permutation Strategy to Improve Conversational Evaluation ECIR 2022
- To Eun Kim (University College London): A Multi-Task Based Neural Model to Simulate Users in Goal-Oriented Dialogue Systems SIGIR 2022
- Akshit Gupta (Delft University of Technology): To Trust or Not To Trust: How a Conversational Interface Affects Trust in a Decision Support System WebConf 2022
Session 2: Applications (11:00-12:30 CEST) [video]
- Abhisek Dash (Indian Institute of Technology Kharagpur): Alexa, in you, I trust! Fairness and Interpretability Issues in E-commerce Search through Smart Speakers WebConf 2022
- Andrea Papenmeier (GESIS - Leibniz-Institute for the Social Sciences): Mhm… ‘ - Conversational Strategies For Product Search Assistants CHIIR 2022
- Alexander Frummet (University of Regensburg): What can I cook with these ingredients?’ - Understanding cooking-related information needs in conversational search TOIS 2022
- Ramesh Manuvinakurike (Intel Labs): Human in the loop approaches in conversational task guidance system preprint 2022
Session 3: Question Answering (13:30-15:00 CEST) [video]
- Gonçalo Raposo (Universidade de Lisboa): Question rewriting? Assessing its importance for conversational question answering ECIR 2022
- Philipp Christmann (Max Planck Institute for Informatics): Conversational Question Answering on Heterogeneous Sources SIGIR 2022
- Hideaki Joko (Radboud University): Conversational Entity Linking: Problem Definition and Datasets SIGIR 2021
- Carlos Gemmell (University of Glasgow): GRILLBot: A flexible conversational agent for solving complex real-world tasks Alexa Prize TaskBot Challenge Proceedings 2022
Session 4: Mixed Initiative (15:30-17:00 CEST) [video]
- Sandeep Avula (Amazon): The Effects of System Initiative during Conversational Collaborative Search CSCW 2022
- Alexander Bondarenko (Martin-Luther-Universität Halle-Wittenberg): A User Study on Clarifying Comparative Questions CHIIR 2022
- Ivan Sekulić (Università della Svizzera italiana Lugano): Evaluating Mixed-initiative Conversational Search Systems via User Simulation WSDM 2022
- Zhenduo Wang (University of Utah): Controlling the Risk of Conversational Search via Reinforcement Learning WebConf 2021
- Svitlana Vakulenko, Amazon Alexa AI
- Ondrej Dusek, Charles University
- Leigh Clark, Swansea University
- Gustavo Penha, Delft University of Technology
- Vaishali Pal, University of Amsterdam
- Vaibhav Adlakha, Mila, McGill University