Neural Machine Translation with External Phrase Memory
This work addresses the challenge of improving translation accuracy in neural machine translation by leveraging external phrase knowledge, representing an incremental advancement in the field.
The paper tackles the problem of incorporating external phrase knowledge into neural machine translation by proposing phraseNet, which uses a phrase memory to store phrase pairs and integrates them into the translation process, resulting in a 3.45 BLEU improvement over a generic neural machine translator on Chinese-to-English translation.
In this paper, we propose phraseNet, a neural machine translator with a phrase memory which stores phrase pairs in symbolic form, mined from corpus or specified by human experts. For any given source sentence, phraseNet scans the phrase memory to determine the candidate phrase pairs and integrates tagging information in the representation of source sentence accordingly. The decoder utilizes a mixture of word-generating component and phrase-generating component, with a specifically designed strategy to generate a sequence of multiple words all at once. The phraseNet not only approaches one step towards incorporating external knowledge into neural machine translation, but also makes an effort to extend the word-by-word generation mechanism of recurrent neural network. Our empirical study on Chinese-to-English translation shows that, with carefully-chosen phrase table in memory, phraseNet yields 3.45 BLEU improvement over the generic neural machine translator.