logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Heterogeneous Graph Neural Network Based Arabic Coreference Resolution

delete2026-01-01
delete0
PRE
AI
E
EL Yousfi, Rihab *
O
Ourekouch, Mounir
E
Erradi, Mohammed
DOI：10.1007/978-3-032-00347-8_17delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
共指消解旨在识别和链接文本中指代同一实体的提及。然而，阿拉伯语共指消解由于数据匮乏和语言复杂性而研究不足。以往工作主要依赖预训练语言模型、多语言变换器以及跨语言迁移学习。然而，这些方法常忽略句法和语义结构，而这些结构对于捕捉更丰富的上下文表示至关重要。本研究聚焦于利用句法和语义信息来改进阿拉伯语的提及链接。我们提出了一种基于异构图模型，联合利用这些特征以增强阿拉伯语共指消解。该模型通过依存树编码句法结构，使用阿拉伯语解析器Camel-Parser 2.0。该模型通过融入语义角色标注（SRL）来优化上下文表示，从而实现更深的语义理解。我们对该方法进行了分析，将其性能与基于BERT的方法和序列到序列模型进行了比较。在阿拉伯语CoNLL-2012共享任务上的实验表明，所提出的模型在F1分数上优于基于BERT的方法，并取得了与当前最佳序列到序列模型相当的结果。
Keyword:
Arabic coreference resolution
Heterogeneous graph
neural network
Dependency parsing
Semantic role labeling (SRL)

期刊

N
NETWORKED SYSTEMS, NETYS 2025
IF:
0
论文数:
16
被引数:
0

机构

M
mohammed vi polytechnic university
学者数:
3.5K
论文数: 2.4K
被引数: 48
引用论文

引用论文

ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic
errProceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
IF0
err2021-01-01
err0
errOAAI
errMuhammad Abdul-Mageed; AbdelRahim Elmadany; El Moatez Billah Nagoudi
err分享
err收藏
End-to-end Neural Coreference Resolution
errProceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
IF0
err2017-01-01
err0
errOAAI
errKenton Lee; Luheng He; Mike Lewis; Luke Zettlemoyer
err分享
err收藏
Word-Level Coreference Resolution
errProceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
IF0
err2021-01-01
err0
errOAAI
errVladimir Dobrovolskii
err分享
err收藏
Exploring Pre-Trained Transformers and Bilingual Transfer Learning for Arabic Coreference Resolution
errProceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference
IF0
err2021-01-01
err0
errOAAI
errBonan Min
err分享
err收藏
CAW-coref: Conjunction-Aware Word-level Coreference ResolutionCAW-coref：基于连词感知的词级共指消解
errProceedings of The Sixth Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC 2023)
IF0
err2023-01-01
err0
errOAAI
errKarel D’Oosterlinck; Semere Kiros Bitew; Brandon Papineau; Christopher Potts; Thomas Demeester; Chris Develder
err分享
err收藏
An Empirical Study of Pre-trained Transformers for Arabic Information Extraction
errProceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
IF0
err2020-01-01
err0
errOAAI
errWuwei Lan; Yang Chen; Wei Xu; Alan Ritter
err分享
err收藏
Revealing the Myth of Higher-Order Inference in Coreference Resolution
errProceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
IF0
err2020-01-01
err0
errOAAI
errLiyan Xu; Jinho D. Choi
err分享
err收藏
Coreference Resolution through a seq2seq Transition-Based System
errTRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS
IF6.9
err2023-03-14
err9
errOAAI
errBohnet, Bernd; Alberti, Chris; Collins, Michael
err分享
err收藏
BERT for Coreference Resolution: Baselines and Analysis
errProceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
IF0
err2019-01-01
err0
errOAAI
errMandar Joshi; Omer Levy; Luke Zettlemoyer; Daniel Weld
err分享
err收藏
Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends
errProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
IF0
err2024-01-01
err0
PREAI
errMartinelli,Giuliano; Barba,Edoardo; Navigli,Roberto
err分享
err收藏
学者 查看更多内容