What Do You Mean `Why?': Resolving Sluices in Conversations
This addresses a specific challenge in conversational AI for improving dialogue systems, but it is incremental as it focuses on a narrow linguistic phenomenon.
The paper tackles the problem of resolving one-word questions like 'Why?' in conversations, which is challenging for computers due to the need to retrieve semantic frames and arguments from context, and introduces a crowd-sourced dataset with annotations from over 4,000 dialogues and strong baseline architectures.
In conversation, we often ask one-word questions such as `Why?' or `Who?'. Such questions are typically easy for humans to answer, but can be hard for computers, because their resolution requires retrieving both the right semantic frames and the right arguments from context. This paper introduces the novel ellipsis resolution task of resolving such one-word questions, referred to as sluices in linguistics. We present a crowd-sourced dataset containing annotations of sluices from over 4,000 dialogues collected from conversational QA datasets, as well as a series of strong baseline architectures.