Improving Lexical Choice in Neural Machine Translation
This addresses translation accuracy for rare words, which is a domain-specific issue in machine translation, with incremental improvements over existing methods.
The paper tackled the problem of mistranslating rare words in neural machine translation by fixing vector norms and integrating a lexical module, achieving improvements of up to +4.3 BLEU across eight language pairs.
We explore two solutions to the problem of mistranslating rare words in neural machine translation. First, we argue that the standard output layer, which computes the inner product of a vector representing the context with all possible output word embeddings, rewards frequent words disproportionately, and we propose to fix the norms of both vectors to a constant value. Second, we integrate a simple lexical module which is jointly trained with the rest of the model. We evaluate our approaches on eight language pairs with data sizes ranging from 100k to 8M words, and achieve improvements of up to +4.3 BLEU, surpassing phrase-based translation in nearly all settings.