Neural End-to-End Coreference Resolution using Morphological Information

Tugba Pamay Arslan; Kutay Acar; Gulsen Eryigit

Neural End-to-End Coreference Resolution using Morphological Information

Tugba Pamay Arslan, Kutay Acar, Gulsen Eryigit

Yapay Zeka ve Veri Mühendisliği Bölümü

Istanbul Technical University

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

2 Atıf (Scopus)

Özet

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.

Orijinal dil	İngilizce
Ana bilgisayar yayını başlığı	EMNLP 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
Editörler	Zabokrtsky Zabokrtsky, Maciej Ogrodniczuk
Yayınlayan	Association for Computational Linguistics (ACL)
Sayfalar	34-40
Sayfa sayısı	7
ISBN (Elektronik)	9781955917025
Yayın durumu	Yayınlandı - 2023
Etkinlik	CRAC Shared Task on Multilingual Coreference Resolution at 6th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2023 - Singapore, Singapore Süre: 7 Ara 2023 → …

Yayın serisi

Adı	EMNLP 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

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	CRAC Shared Task on Multilingual Coreference Resolution at 6th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2023
Ülke/Bölge	Singapore
Şehir	Singapore
Periyot	7/12/23 → …

Bibliyografik not

Publisher Copyright:
© CRAC 2023. All Rights Reserved.

Finansman

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.

Finansörler	Finansör numarası
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 Üniversitesi	4015042023
European Cooperation in Science and Technology	123E079
Türkiye Bilimsel ve Teknolojik Araştırma Kurumu
˙TÜ Artificial Intelligence and Data Science Application and Research Center

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Arslan, T. P., Acar, K., & Eryigit, G. (2023). Neural End-to-End Coreference Resolution using Morphological Information. In Z. Zabokrtsky, & M. Ogrodniczuk (Eds.), EMNLP 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 (pp. 34-40). (EMNLP 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). Association for Computational Linguistics (ACL).

Arslan, Tugba Pamay ; Acar, Kutay ; Eryigit, Gulsen. / Neural End-to-End Coreference Resolution using Morphological Information. EMNLP 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. editör / Zabokrtsky Zabokrtsky ; Maciej Ogrodniczuk. Association for Computational Linguistics (ACL), 2023. pp. 34-40 (EMNLP 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).

@inproceedings{09917d1e74084725bbae1aa0ba068571,

title = "Neural End-to-End Coreference Resolution using Morphological Information",

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.",

author = "Arslan, {Tugba Pamay} and Kutay Acar and Gulsen Eryigit",

note = "Publisher Copyright: {\textcopyright} CRAC 2023. All Rights Reserved.; CRAC Shared Task on Multilingual Coreference Resolution at 6th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2023 ; Conference date: 07-12-2023",

year = "2023",

language = "English",

series = "EMNLP 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",

publisher = "Association for Computational Linguistics (ACL)",

pages = "34--40",

editor = "Zabokrtsky Zabokrtsky and Maciej Ogrodniczuk",

booktitle = "EMNLP 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",

address = "United States",

}

Arslan, TP, Acar, K & Eryigit, G 2023, Neural End-to-End Coreference Resolution using Morphological Information. in Z Zabokrtsky & M Ogrodniczuk (eds), EMNLP 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. EMNLP 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, Association for Computational Linguistics (ACL), pp. 34-40, CRAC Shared Task on Multilingual Coreference Resolution at 6th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2023, Singapore, Singapore, 7/12/23.

Neural End-to-End Coreference Resolution using Morphological Information. / Arslan, Tugba Pamay; Acar, Kutay; Eryigit, Gulsen.
EMNLP 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. ed. / Zabokrtsky Zabokrtsky; Maciej Ogrodniczuk. Association for Computational Linguistics (ACL), 2023. p. 34-40 (EMNLP 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).

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

TY - GEN

T1 - Neural End-to-End Coreference Resolution using Morphological Information

AU - Arslan, Tugba Pamay

AU - Acar, Kutay

AU - Eryigit, Gulsen

PY - 2023

Y1 - 2023

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85184809579&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85184809579

T3 - EMNLP 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

SP - 34

EP - 40

BT - EMNLP 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

A2 - Zabokrtsky, Zabokrtsky

A2 - Ogrodniczuk, Maciej

PB - Association for Computational Linguistics (ACL)

T2 - CRAC Shared Task on Multilingual Coreference Resolution at 6th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2023

Y2 - 7 December 2023

ER -

Arslan TP, Acar K, Eryigit G. Neural End-to-End Coreference Resolution using Morphological Information. In Zabokrtsky Z, Ogrodniczuk M, editörler, EMNLP 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. Association for Computational Linguistics (ACL). 2023. p. 34-40. (EMNLP 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).

Neural End-to-End Coreference Resolution using Morphological Information

Özet

Yayın serisi

???event.eventtypes.event.conference???

Bibliyografik not

Finansman

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap