Neural End-to-End Coreference Resolution using Morphological Information

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

2 Citations (Scopus)

Abstract

In morphologically rich languages, words consist of morphemes containing deeper information in morphology, and thus such languages may necessitate the use of morpheme-level representations as well as word representations. This study introduces a neural multilingual end-to-end coreference resolution system by incorporating morphological information in transformer-based word embeddings on the baseline model. This proposed model participated in the Sixth Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC 2023). Including morphological information explicitly into the coreference resolution improves the performance, especially in morphologically rich languages (e.g., Catalan, Hungarian, and Turkish). The introduced model outperforms the baseline system by 2.57 percentage points on average by obtaining 59.53% CoNLL F-score.

Original languageEnglish
Title of host publicationEMNLP 2023 - Proceedings of the CRAC 2023 Shared Task on Multilingual Coreference Resolution at 6th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2023
EditorsZabokrtsky Zabokrtsky, Maciej Ogrodniczuk
PublisherAssociation for Computational Linguistics (ACL)
Pages34-40
Number of pages7
ISBN (Electronic)9781955917025
Publication statusPublished - 2023
EventCRAC Shared Task on Multilingual Coreference Resolution at 6th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2023 - Singapore, Singapore
Duration: 7 Dec 2023 → …

Publication series

NameEMNLP 2023 - Proceedings of the CRAC 2023 Shared Task on Multilingual Coreference Resolution at 6th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2023

Conference

ConferenceCRAC Shared Task on Multilingual Coreference Resolution at 6th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2023
Country/TerritorySingapore
CitySingapore
Period7/12/23 → …

Bibliographical note

Publisher Copyright:
© CRAC 2023. All Rights Reserved.

Funding

This work is funded by the Scientific and Technological Research Council of Turkey (TUBITAK) with a TUBITAK 2515 (European Cooperation in Science and Technology - COST) project Grant No. 123E079. Computing resources used in this work were provided by the National Center for High Performance Computing of Turkey (UHeM) under grant number 4015042023 and also by İTÜ Artificial Intelligence and Data Science Application and Research Center. This work is funded by the Scientific and Technological Research Council of Turkey (TUBITAK) with a TUBITAK 2515 (European Cooperation in Science and Technology - COST) project Grant No. 123E079. Computing resources used in this work were provided by the National Center for High Performance Computing of Turkey (UHeM) under grant number 4015042023 and also by ˙TÜ Artificial Intelligence and Data Science Application and Research Center.

FundersFunder number
İTÜ Artificial Intelligence and Data Science Application and Research Center
National Center for High Performance Computing of Turkey
TUBITAK 2515
Ulusal Yüksek Başarımlı Hesaplama Merkezi, Istanbul Teknik Üniversitesi4015042023
European Cooperation in Science and Technology123E079
Türkiye Bilimsel ve Teknolojik Araştırma Kurumu
˙TÜ Artificial Intelligence and Data Science Application and Research Center

    Fingerprint

    Dive into the research topics of 'Neural End-to-End Coreference Resolution using Morphological Information'. Together they form a unique fingerprint.

    Cite this