AmbiCoref: Evaluating Human and Model Sensitivity to Ambiguous Coreference

Yuewei Yuan, Chaitanya Malaviya, Mark Yatskar


Abstract
Given a sentence “Abby told Brittney that she upset Courtney”, one would struggle to understand who “she” refers to, and ask for clarification. However, if the word “upset” were replaced with “hugged”, “she” unambiguously refers to Abby. We study if modern coreference resolution models are sensitive to such pronominal ambiguity. To this end, we construct AmbiCoref, a diagnostic corpus of minimal sentence pairs with ambiguous and unambiguous referents. Our examples generalize psycholinguistic studies of human perception of ambiguity around particular arrangements of verbs and their arguments. Analysis shows that (1) humans are less sure of referents in ambiguous AmbiCoref examples than unambiguous ones, and (2) most coreference models show little difference in output between ambiguous and unambiguous pairs. We release AmbiCoref as a diagnostic corpus for testing whether models treat ambiguity similarly to humans.
Anthology ID:
2023.findings-eacl.75
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1023–1030
Language:
URL:
https://aclanthology.org/2023.findings-eacl.75
DOI:
10.18653/v1/2023.findings-eacl.75
Bibkey:
Cite (ACL):
Yuewei Yuan, Chaitanya Malaviya, and Mark Yatskar. 2023. AmbiCoref: Evaluating Human and Model Sensitivity to Ambiguous Coreference. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1023–1030, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
AmbiCoref: Evaluating Human and Model Sensitivity to Ambiguous Coreference (Yuan et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.75.pdf
Video:
 https://aclanthology.org/2023.findings-eacl.75.mp4