How Lexical is Bilingual Lexicon Induction?
This work addresses the problem of bilingual lexicon induction for low-resource language pairs, representing an incremental improvement.
The paper tackled the challenge of bilingual lexicon induction (BLI) in low-resource settings by incorporating additional lexical information into a retrieve-and-rank approach, improving over the previous state of the art by an average of 2% across all language pairs on the XLING dataset.
In contemporary machine learning approaches to bilingual lexicon induction (BLI), a model learns a mapping between the embedding spaces of a language pair. Recently, retrieve-and-rank approach to BLI has achieved state of the art results on the task. However, the problem remains challenging in low-resource settings, due to the paucity of data. The task is complicated by factors such as lexical variation across languages. We argue that the incorporation of additional lexical information into the recent retrieve-and-rank approach should improve lexicon induction. We demonstrate the efficacy of our proposed approach on XLING, improving over the previous state of the art by an average of 2\% across all language pairs.