Using word embeddings for improving statistical machine translation of phrasal verbs

Abstract

We examine the employment of word embeddings for machine translation (MT) of phrasal verbs (PVs), a linguistic phenomenon with challenging semantics. Using word embeddings, we augment the translation model with two features: one modelling distributional semantic properties of the source and target phrase and another modelling the degree of compositionality of PVs. We also obtain paraphrases to increase the amount of relevant training data. Our method leads to improved translation quality for PVs in a case study with English to Bulgarian MT system.