TY - GEN

T1 - What Do You Mean ‘Why?’

T2 - Thirty-Forth AAAI Conference on Artificial Intelligence

AU - Hansen, Victor Petrén Bach

AU - Søgaard, Anders

PY - 2020

Y1 - 2020

N2 - 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.

AB - 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.

U2 - 10.1609/aaai.v34i05.6295

DO - 10.1609/aaai.v34i05.6295

M3 - Article in proceedings

SP - 7887-7894.

BT - Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2020)

PB - AAAI Press

Y2 - 7 February 2020 through 12 February 2020

ER -