Evaluating coreference resolvers on community-based question answering: From rule-based to state of the art


Coreference resolution is a key step in natural language understanding. Developments in coreference resolution are mainly focused on improving the performance on standard datasets annotated for coreference resolution. However, coreference resolution is an intermediate step for text understanding and it is not clear how these improvements translate into downstream task performance. In this paper, we perform a thorough investigation on the impact of coreference resolvers in multiple settings of community-based question answering task, i.e., answer selection with long answers. Our settings cover multiple text domains and encompass several answer selection methods. We first inspect extrinsic evaluation of coreference resolvers on answer selection by using coreference relations to decontextualize individual sentences of candidate answers, and then annotate a subset of answers with coreference information for intrinsic evaluation. The results of our extrinsic evaluation show that while there is a significant difference between the performance of the rule-based system vs. state-of-the-art neural model on coreference resolution datasets, we do not observe a considerable difference on their impact on downstream models. Our intrinsic evaluation shows that (i) resolving coreference relations on less-formal text genres is more difficult even for trained annotators, and (ii) the values of linguistic-agnostic coreference evaluation metrics do not correlate with the impact on downstream data.

SEEK ID: https://publications.h-its.org/publications/1592

Projects: Natural Language Processing

Publication type: InProceedings

Citation: Proceedings of the Fifth Workshop on Computational Models of Reference, Anaphora and Coreference, Gyeongju, Republic of Korea, 16--17 Octrober, 2022, pp.61--73

Date Published: 16th Oct 2022

URL: https://aclanthology.org/2022.crac-1.7

Registered Mode: manually

Authors: Haixia Chai, Nafise Sadat Moosavi, Iryna Gurevych, Michael Strube

help Submitter

Views: 224

Created: 6th Feb 2023 at 14:35

help Tags

This item has not yet been tagged.

help Attributions


Powered by
Copyright © 2008 - 2022 The University of Manchester and HITS gGmbH