Coreference Resolution for Vietnamese Narrative Texts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tran, Hieu-Dai, Nguyen, Duc-Vu, Nguyen, Ngan Luu-Thuy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908340243660800
author Tran, Hieu-Dai
Nguyen, Duc-Vu
Nguyen, Ngan Luu-Thuy
author_facet Tran, Hieu-Dai
Nguyen, Duc-Vu
Nguyen, Ngan Luu-Thuy
contents Coreference resolution is a vital task in natural language processing (NLP) that involves identifying and linking different expressions in a text that refer to the same entity. This task is particularly challenging for Vietnamese, a low-resource language with limited annotated datasets. To address these challenges, we developed a comprehensive annotated dataset using narrative texts from VnExpress, a widely-read Vietnamese online news platform. We established detailed guidelines for annotating entities, focusing on ensuring consistency and accuracy. Additionally, we evaluated the performance of large language models (LLMs), specifically GPT-3.5-Turbo and GPT-4, on this dataset. Our results demonstrate that GPT-4 significantly outperforms GPT-3.5-Turbo in terms of both accuracy and response consistency, making it a more reliable tool for coreference resolution in Vietnamese.
format Preprint
id arxiv_https___arxiv_org_abs_2504_19606
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Coreference Resolution for Vietnamese Narrative Texts
Tran, Hieu-Dai
Nguyen, Duc-Vu
Nguyen, Ngan Luu-Thuy
Computation and Language
Coreference resolution is a vital task in natural language processing (NLP) that involves identifying and linking different expressions in a text that refer to the same entity. This task is particularly challenging for Vietnamese, a low-resource language with limited annotated datasets. To address these challenges, we developed a comprehensive annotated dataset using narrative texts from VnExpress, a widely-read Vietnamese online news platform. We established detailed guidelines for annotating entities, focusing on ensuring consistency and accuracy. Additionally, we evaluated the performance of large language models (LLMs), specifically GPT-3.5-Turbo and GPT-4, on this dataset. Our results demonstrate that GPT-4 significantly outperforms GPT-3.5-Turbo in terms of both accuracy and response consistency, making it a more reliable tool for coreference resolution in Vietnamese.
title Coreference Resolution for Vietnamese Narrative Texts
topic Computation and Language
url https://arxiv.org/abs/2504.19606