SCAI-QReCC Shared Task on Conversational Question Answering
This work addresses a research gap in evaluating conversational AI systems, but it is incremental as it builds upon existing datasets and methods.
The paper tackled the challenge of evaluating answer correctness in conversational question answering by conducting a shared task and crowdsourcing experiments to collect annotations for answer plausibility and faithfulness, resulting in an extension of the original dataset with alternative correct answers from participant systems.
Search-Oriented Conversational AI (SCAI) is an established venue that regularly puts a spotlight upon the recent work advancing the field of conversational search. SCAI'21 was organised as an independent on-line event and featured a shared task on conversational question answering. Since all of the participant teams experimented with answer generation models for this task, we identified evaluation of answer correctness in this settings as the major challenge and a current research gap. Alongside the automatic evaluation, we conducted two crowdsourcing experiments to collect annotations for answer plausibility and faithfulness. As a result of this shared task, the original conversational QA dataset used for evaluation was further extended with alternative correct answers produced by the participant systems.