arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.07214cs.CLcs.AI

面向零样本命名实体识别的跨语言IPA对比学习

Cross-Lingual IPA Contrastive Learning for Zero-Shot NER

LG Innotek;Carnegie Mellon University(卡内基梅隆大学)

Jimin Sohn, David R. Mortensen

AI总结:

本文提出CONLIPA数据集和IPAC跨语言IPA对比学习方法,通过缩小相似语音特征语言间的音位表示差距,提升高资源语言模型在低资源语言零样本NER上的性能,并取得显著平均增益。

摘要:

现有的面向低资源语言的零样本命名实体识别(NER)方法主要依赖机器翻译,而近期方法已将重点转向音位表示。在此基础上,我们研究了在具有相似语音特征的语言之间缩小IPA转写中的音位表示差距,如何使在低资源语言上训练的高资源语言模型能够有效执行。在这项工作中,我们提出了CONtrastive Learning with IPA(CONLIPA)数据集,该数据集包含来自10个常用语系的10种英语和高资源语言的IPA对。我们还提出了一种使用CONLIPA数据集的跨语言IPA对比学习方法(IPAC)。此外,我们提出的数据集和方法与表现最佳的基线相比,展示了显著的平均增益。

英文摘要:

Existing approaches to zero-shot Named Entity Recognition (NER) for low-resource languages have primarily relied on machine translation, whereas more recent methods have shifted focus to phonemic representation. Building upon this, we investigate how reducing the phonemic representation gap in IPA transcription between languages with similar phonetic characteristics enables models trained on high-resource languages to perform effectively on low-resource languages. In this work, we propose CONtrastive Learning with IPA (CONLIPA) dataset containing 10 English and high resource languages IPA pairs from 10 frequently used language families. We also propose a cross-lingual IPA Contrastive learning method (IPAC) using the CONLIPA dataset. Furthermore, our proposed dataset and methodology demonstrate a substantial average gain when compared to the best performing baseline.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑