A Predictive Model for Notional Anaphora in English

Amir Zeldes


Abstract
Notional anaphors are pronouns which disagree with their antecedents’ grammatical categories for notional reasons, such as plural to singular agreement in: “the government ... they”. Since such cases are rare and conflict with evidence from strictly agreeing cases (“the government ... it”), they present a substantial challenge to both coreference resolution and referring expression generation. Using the OntoNotes corpus, this paper takes an ensemble approach to predicting English notional anaphora in context on the basis of the largest empirical data to date. In addition to state of the art prediction accuracy, the results suggest that theoretical approaches positing a plural construal at the antecedent’s utterance are insufficient, and that circumstances at the anaphor’s utterance location, as well as global factors such as genre, have a strong effect on the choice of referring expression.
Anthology ID:
W18-0704
Volume:
Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Massimo Poesio, Vincent Ng, Maciej Ogrodniczuk
Venue:
CRAC
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
34–43
Language:
URL:
https://aclanthology.org/W18-0704
DOI:
10.18653/v1/W18-0704
Bibkey:
Cite (ACL):
Amir Zeldes. 2018. A Predictive Model for Notional Anaphora in English. In Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference, pages 34–43, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
A Predictive Model for Notional Anaphora in English (Zeldes, CRAC 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/proper-vol2-ingestion/W18-0704.pdf