基于替换的多语言词义归纳方法
Multilingual Substitution-based Word Sense Induction
AI总结：
针对现有词义归纳方法难适配新语言的问题，提出基于替换的多语言WSI方法，依托覆盖百种语言的多语言模型，少适配即可用，在英语数据集上性能比肩单语方法，更适配低资源语言需求。
摘要：
词义归纳（Word Sense Induction，WSI）是通过将歧义词的使用情况聚类为对应不同词义的簇，来发现该词词义的任务。目前已有诸多针对英语及少数其他语言的WSI解决方法，但这些方法难以适配新语言。我们提出了基于替换的多语言WSI方法，依托底层多语言语言模型覆盖的100种语言，仅需极少甚至无需适配即可支持其中任意语言。尽管具备多语言能力，我们的方法在主流英语WSI数据集上的表现与现有单语言方法相当。同时，这类方法对低资源语言尤为有用——这类语言缺乏英语所拥有的词汇资源，因此对WSI这类无监督方法的需求更高。
英文摘要：
Word Sense Induction (WSI) is the task of discovering senses of an ambiguous word by grouping usages of this word into clusters corresponding to these senses. Many approaches were proposed to solve WSI in English and a few other languages, but these approaches are not easily adaptable to new languages. We present multilingual substitution-based WSI methods that support any of 100 languages covered by the underlying multilingual language model with minimal to no adaptation required. Despite the multilingual capabilities, our methods perform on par with the existing monolingual approaches on popular English WSI datasets. At the same time, they will be most useful for lower-resourced languages which miss lexical resources available for English, thus, have higher demand for unsupervised methods like WSI.
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。
