In this paper, we advocate for using large pre-trained monolingual language
models in cross lingual zero-shot word sense disambiguation (WSD) coupled with
a contextualized mapping mechanism. We also report rigorous experiments that
illustrate the effectiveness of employing sparse contextualized word
representations obtained via a dictionary learning procedure. Our experimental
results demonstrate that the above modifications yield a significant
improvement of nearly 6.5 points of increase in the average F-score (from 62.0
to 68.5) over a collection of 17 typologically diverse set of target languages.
We release our source code for replicating our experiments at
this https URL

我们提倡在跨语言零 - shot 词义消歧中使用大型预训练单语语言模型，并结合一种上下文映射机制。我们通过字典学习过程获得了稀疏上下文化词表示，并进行了严格的实验，证明了上述改进带来了显著的提升，平均 F 分数增加了近 6.5 个百分点（从 62.0 增加到 68.5），涵盖了 17 种语言。我们在此网址发布了复制实验的源代码。