Using Distributional Similarity of Multi-Way Translations to Predict Multiword Expression Compositionality

We predict the compositionality of multi-word expressions using distributional sim-ilarity between each component word and the overall expression, based on transla-tions into multiple languages. We evaluate the method over English noun compounds, English verb particle constructions and German noun compounds. We show that the estimation of compositionality is im-proved when using translations into multi-ple languages, as compared to simply us-ing distributional similarity in the source language. We further find that string sim-ilarity complements distributional similar-ity. 1 Compositionality of MWEs Multiword expressions (hereafter MWEs) are combinations of words which are lexically, syntac-tically, semantically or statistically idiosyncratic (Sag et al., 2002; Baldwin and Kim, 2009). Much research has been carried out on the extraction and identification of MWEs1 in English (Schone an