Ellipsis Resolution as Question Answering: An Evaluation

Rahul Aralikatte, Matthew Lamm, Daniel Hardt, Anders Søgaard

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

106 Downloads (Pure)

Abstract

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).
Original languageEnglish
Title of host publicationProceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics
EditorsPaola Merlo, Jorg Tiedemann, Reut Tsarfaty
Number of pages8
Place of PublicationStroudsburg, PA
PublisherAssociation for Computational Linguistics
Publication date2021
Pages810-817
ISBN (Electronic)9781954085022
DOIs
Publication statusPublished - 2021
Event16th Conference of the European Chapter of the Association for Computational Linguistics (EACL) - Online, WWW
Duration: 19 Apr 202123 Apr 2021
Conference number: 16

Conference

Conference16th Conference of the European Chapter of the Association for Computational Linguistics (EACL)
Number16
LocationOnline
Country/TerritoryWWW
Period19/04/202123/04/2021

Cite this