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

Abstract

We predict the compositionality of multiword expressions using distributional similarity between each component word and the overall expression, based on translations 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 improved when using translations into multiple languages, as compared to simply using distributional similarity in the source language. We further find that string similarity complements distributional similarity.

The Role of Modifier and Head Properties in Predicting the Compositionality of English and German Noun-Noun Compounds: A Vector-Space Perspective

“…Computational approaches to automatically predict the compositionality of noun compounds have mostly been realised as vector space models, and can be subdivided into two subfields: (i) approaches that aim to predict the meaning of a compound by composite functions, relying on the vectors of the constituents (e.g., Mitchell and Lapata (2010), Coecke et al (2011), Baroni et al (2014), and Hermann (2014)); and (ii) approaches that aim to predict the degree of compositionality of a compound, typically by comparing the compound vectors with the constituent vectors (e.g., Reddy et al (2011), Salehi and Cook (2013), Schulte im Walde et al (2013), Salehi et al (2014;2015a)). In line with subfield (ii), this paper aims to distinguish the contributions of modifier and head properties when predicting the compositionality of English and German nounnoun compounds in a vector space model.…”

Distinguishing Degrees of Compositionality in Compound Splitting for Statistical Machine Translation

“…Zinsmeister and Heid (2004) used subcategorising verbs to predict compound-head similarities of German noun compounds. Most recently, Salehi et al (2014) extended the previous approaches to take multi-lingual co-occurrence information into account, regarding English and German noun compounds, and English particle verbs.…”

“…Among many other tasks, distributional semantic information has been utilised to determine the degree of compositionality (or: semantic transparency) of various types of compounds, most notably regarding noun compounds (e.g., Zinsmeister and Heid (2004), Reddy et al (2011), Schulte im Walde et al (2013), Salehi et al (2014)) and particle verbs (e.g., McCarthy et al (2003), Bannard (2005), Cook and Stevenson (2006), Kühner and Schulte im Walde (2010), Bott and Schulte im Walde (2014), Salehi et al (2014)). Typically, these approaches rely on co-occurrence information from a corpus (either referring to bagsof-words, or focusing on target-specific types of features), and compare the distributional features of the compounds with those of the constituents, in order to predict the degree of compositionality of the…”

Proceedings of the First Workshop on Computational Approaches to Compound Analysis (ComAComA 2014)

“…Among many other tasks, distributional semantic information has been utilised to determine the degree of compositionality (or: semantic transparency) of various types of compounds, most notably regarding noun compounds (e.g., Zinsmeister and Heid (2004), Reddy et al (2011) Salehi et al (2014)). Typically, these approaches rely on co-occurrence information from a corpus (either referring to bagsof-words, or focusing on target-specific types of features), and compare the distributional features of the compounds with those of the constituents, in order to predict the degree of compositionality of the…”