Bilingual Lexicon Induction by Learning to Combine Word-Level and Character-Level Representations
Geert Heyman, Ivan Vulić, Marie‐Francine Moens · 2017
We study the problem of bilingual lexicon induction (BLI) in a setting where some translation resources are available, but unknown translations are sought for certain, possibly domain-specific terminology.We frame BLI as a classification problem for which we design a neural network based classification architecture composed of recurrent long short-term memory and deep feed forward networks.The results show that word-and character-level representations each improve state-of-the-art results for BLI, and the best results are obtained by exploiting the synergy between these wordand character-level representations in the classification model.