arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.07424cs.CL
收藏

MINERS:作为语义检索器的多语言语言模型

MINERS: Multilingual Language Models as Semantic Retrievers

Capital One;Brown University(布朗大学);University College London(伦敦大学学院)

Genta Indra Winata, Ruochen Zhang, David Ifeoluwa Adelani

AI总结:

本文提出MINERS基准,全面评估多语言语言模型在200多种语言的语义检索任务中的能力,发现仅检索语义相似嵌入即可媲美最先进方法且无需微调。

摘要:

单词一直被表示在编码其语义相似性的高维向量空间中,从而支持下游应用,如检索同义词、反义词和相关上下文。然而,尽管多语言语言模型(LMs)最近取得了进展,但这些模型的表示在语义检索环境中的有效性尚未得到全面探索。为了填补这一空白,本文引入了MINERS,这是一个旨在评估多语言LMs在语义检索任务中能力的基准,包括双语文本挖掘和通过检索增强上下文的分类。我们创建了一个全面的框架来评估LMs在200多种不同语言中检索样本的鲁棒性,包括在具有挑战性的跨语言和语码转换环境中的极低资源语言。我们的结果表明,仅检索语义相似的嵌入即可产生与最先进方法相媲美的性能,而无需任何微调。

英文摘要:

Words have been represented in a high-dimensional vector space that encodes their semantic similarities, enabling downstream applications such as retrieving synonyms, antonyms, and relevant contexts. However, despite recent advances in multilingual language models (LMs), the effectiveness of these models' representations in semantic retrieval contexts has not been comprehensively explored. To fill this gap, this paper introduces the MINERS, a benchmark designed to evaluate the ability of multilingual LMs in semantic retrieval tasks, including bitext mining and classification via retrieval-augmented contexts. We create a comprehensive framework to assess the robustness of LMs in retrieving samples across over 200 diverse languages, including extremely low-resource languages in challenging cross-lingual and code-switching settings. Our results demonstrate that by solely retrieving semantically similar embeddings yields performance competitive with state-of-the-art approaches, without requiring any fine-tuning.

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。

↑