Ellipsis resolution as question answering: An evaluation
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Ellipsis resolution as question answering : An evaluation. / Aralikatte, Rahul; Lamm, Matthew; Hardt, Daniel; Søgaard, Anders.
EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics, 2021. p. 810-817.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Ellipsis resolution as question answering
T2 - 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021
AU - Aralikatte, Rahul
AU - Lamm, Matthew
AU - Hardt, Daniel
AU - Søgaard, Anders
PY - 2021
Y1 - 2021
N2 - 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).
AB - 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).
UR - http://www.scopus.com/inward/record.url?scp=85107308576&partnerID=8YFLogxK
U2 - 10.18653/v1/2021.eacl-main.68
DO - 10.18653/v1/2021.eacl-main.68
M3 - Article in proceedings
AN - SCOPUS:85107308576
SP - 810
EP - 817
BT - EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics
Y2 - 19 April 2021 through 23 April 2021
ER -
ID: 287066069