arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.09388cs.CL
收藏

针对极低资源语言的多语言语言模型的有效词汇扩展

Effective vocabulary expansion of multilingual language models for extremely low-resource languages

School of Foreign Languages, University of Electronic Science and Technology of China(电子科技大学外国语言学院);School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院)

Jianyu Zheng

AI总结:

提出通过筛选源语言偏置词汇并利用双语词典初始化扩展词汇表示,对多语言预训练模型进行持续预训练,在词性标注和命名实体识别任务上分别提升0.54%和2.60%。

摘要:

多语言预训练语言模型(mPLMs)为许多低资源语言带来了显著的好处。为了进一步扩展这些模型能够支持的语言范围,许多工作集中于对这些模型进行持续预训练。然而,很少有工作解决如何将mPLMs扩展到之前不支持的低资源语言。为了解决这个问题,我们使用目标语言语料库扩展模型的词汇表。然后,我们从模型的原始词汇表中筛选出一个子集,该子集偏向于表示源语言(例如英语),并利用双语词典初始化扩展词汇的表示。随后,我们基于这些扩展词汇的表示,使用目标语言语料库继续预训练mPLMs。实验结果表明,我们提出的方法在词性标注和命名实体识别任务上优于使用随机初始化扩展词汇进行持续预训练的基线方法,分别提高了0.54%和2.60%。此外,我们的方法在选择训练语料库时表现出高鲁棒性,并且模型在源语言上的性能在持续预训练后没有下降。

英文摘要:

Multilingual pre-trained language models(mPLMs) offer significant benefits for many low-resource languages. To further expand the range of languages these models can support, many works focus on continued pre-training of these models. However, few works address how to extend mPLMs to low-resource languages that were previously unsupported. To tackle this issue, we expand the model's vocabulary using a target language corpus. We then screen out a subset from the model's original vocabulary, which is biased towards representing the source language(e.g. English), and utilize bilingual dictionaries to initialize the representations of the expanded vocabulary. Subsequently, we continue to pre-train the mPLMs using the target language corpus, based on the representations of these expanded vocabulary. Experimental results show that our proposed method outperforms the baseline, which uses randomly initialized expanded vocabulary for continued pre-training, in POS tagging and NER tasks, achieving improvements by 0.54% and 2.60%, respectively. Furthermore, our method demonstrates high robustness in selecting the training corpora, and the models' performance on the source language does not degrade after continued pre-training.

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。

↑