Pre-training mention representations in coreference models

Yuval Varkel, Amir Globerson

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Collecting labeled data for coreference resolution is a challenging task, requiring skilled annotators. It is thus desirable to develop coreference resolution models that can make use of unlabeled data. Here we provide such an approach for the powerful class of neural coreference models. These models rely on representations of mentions, and we show these representations can be learned in a self-supervised manner towards improving resolution accuracy. We propose two self-supervised tasks that are closely related to coreference resolution and thus improve mention representation. Applying this approach to the GAP dataset results in new state of the arts results.

Original languageEnglish
Title of host publicationEMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages8534-8540
Number of pages7
ISBN (Electronic)9781952148606
StatePublished - 2020
Event2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020 - Virtual, Online
Duration: 16 Nov 202020 Nov 2020

Publication series

NameEMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Conference

Conference2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020
CityVirtual, Online
Period16/11/2020/11/20

Fingerprint

Dive into the research topics of 'Pre-training mention representations in coreference models'. Together they form a unique fingerprint.

Cite this