Lexical Chains meet Word Embeddings in Document-level Statistical Machine Translation

The phrase-based Statistical Machine Translation (SMT) approach deals with sentences in isolation, making it difficult to consider discourse context in translation. This poses a challenge for ambiguous words that need discourse knowledge to be correctly translated. We propose a method that benefits from the semantic similarity in lexical chains to improve SMT output by integrating it in a document-level decoder. We focus on word embeddings to deal with the lexical chains, contrary to the traditional approach that uses lexical resources. Experimental results on German→English show that our method produces correct translations in up to 88% of the changes, improving the translation in 36%-48% of them over the baseline.