Ellipsis Resolution as Question Answering: An Evaluation

Rahul Aralikatte, Matthew Lamm, Daniel Hardt, Anders Søgaard

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

Abstrakt

Most, if not all forms of ellipsis (e.g., ‘so does Mary’) are similar to reading comprehension questions (‘what does Mary do’), in that in order to resolve them, we need to identify an appropriate text span in the preceding discourse. Following this observation, we present an alternative approach for English ellipsis resolution relying on architectures developed for question answering (QA). We present both single-task models, and joint models trained on auxiliary QA and coreference resolution datasets, clearly outperforming the current state of the art for Sluice Ellipsis (from 70.00 to 86.01 F1) and Verb Phrase Ellipsis (from 72.89 to 78.66 F1).
OriginalsprogEngelsk
TitelProceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics
RedaktørerPaola Merlo, Jorg Tiedemann, Reut Tsarfaty
Antal sider8
UdgivelsesstedStroudsburg, PA
ForlagAssociation for Computational Linguistics
Publikationsdato2021
Sider810-817
ISBN (Elektronisk)9781954085022
StatusUdgivet - 2021
Begivenhed16th conference of the European Chapter of the Association for Computational Linguistics (EACL) - Online, WWW
Varighed: 19 apr. 202123 apr. 2021
Konferencens nummer: 16

Konference

Konference16th conference of the European Chapter of the Association for Computational Linguistics (EACL)
Nummer16
LokationOnline
LandWWW
Periode19/04/202123/04/2021

Citationsformater