Context-Dependent Word Representation for Neural Machine Translation

TL;DR

This paper introduces context-dependent word representations and symbolization techniques to improve neural machine translation, addressing the ambiguity in word embeddings and enhancing translation accuracy.

Contribution

It proposes a novel method to contextualize word embeddings and represent special tokens with typed symbols, significantly improving translation quality.

Findings

Improved translation quality on En-Fr and En-De datasets.

Contextualized embeddings better disambiguate word meanings.

Typed symbols aid in translating non-standard words.

Abstract

We first observe a potential weakness of continuous vector representations of symbols in neural machine translation. That is, the continuous vector representation, or a word embedding vector, of a symbol encodes multiple dimensions of similarity, equivalent to encoding more than one meaning of the word. This has the consequence that the encoder and decoder recurrent networks in neural machine translation need to spend substantial amount of their capacity in disambiguating source and target words based on the context which is defined by a source sentence. Based on this observation, in this paper we propose to contextualize the word embedding vectors using a nonlinear bag-of-words representation of the source sentence. Additionally, we propose to represent special tokens (such as numbers, proper nouns and acronyms) with typed symbols to facilitate translating those words that are not well-suited to be translated via continuous vectors. The experiments on En-Fr and En-De reveal that the proposed approaches of contextualization and symbolization improves the translation quality of neural machine translation systems significantly.