Automating Interlingual Homograph Recognition with Parallel Sentences
Yi Han, Ryohei Sasano, Koichi Takeda · 2022
Interlingual homographs are words that spell the same but possess different meanings across languages.Recognizing interlingual homographs from form-identical words generally needs linguistic knowledge and massive annotation work.In this paper, we propose an automatic interlingual homograph recognition method based on the cross-lingual word embedding similarity and co-occurrence of formidentical words in parallel sentences.We conduct experiments with off-the-shelf language models coordinating with cross-lingual alignment operations and co-occurrence metrics on the Chinese-Japanese and English-Dutch language pairs.Experimental results demonstrate that our proposed method can achieve accurate and consistent predictions across languages.