Predicting Machine Translation Adequacy with Document Embeddings

Using Word Embeddings to Enforce Document-Level Lexical Consistency in Machine Translation

We integrate newmechanisms in a document-level machine translation decoder to improve the lexical consistency of document translations. First, we develop a document-level feature designed to score the lexical consistency of a translation. This feature, which applies towords that have been translated into different forms within the document, uses word embeddings to measure the adequacy of each w...

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 docum...

Document Embeddings as a Means of Domain Adaptation for the Machine Translation

Bilingual Word Embeddings from Parallel and Non-parallel Corpora for Cross-Language Text Classification

In many languages, sparse availability of resources causes numerous challenges for textual analysis tasks. Text classification is one of such standard tasks that is hindered due to limited availability of label information in lowresource languages. Transferring knowledge (i.e. label information) from high-resource to low-resource languages might improve text classification as compared to the ot...

Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings

Word sense disambiguation is necessary in translation because different word senses often have different translations. Neural machine translation models learn different senses of words as part of an end-to-end translation task, and their capability to perform word sense disambiguation has so far not been quantified. We exploit the fact that neural translation models can score arbitrary translat...