Research Repository

Unsupervised Compositionality Prediction of Nominal Compounds

Cordeiro, Silvio and Villavicencio, Aline and Idiart, Marco and Ramisch, Carlos (2019) 'Unsupervised Compositionality Prediction of Nominal Compounds.' Computational Linguistics, 45 (1). 1 - 57. ISSN 0891-2017

[img]
Preview
Text
coli_a_00341.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB) | Preview

Abstract

Nominal compounds such as red wine and nut case display a continuum of compositionality, with varying contributions from the components of the compound to its semantics. This article proposes a framework for compound compositionality prediction using distributional semantic models, evaluating to what extent they capture idiomaticity compared to human judgments. For evaluation, we introduce datasets containing human judgments in three languages: English, French and Portuguese. The results obtained reveal a high agreement between the models and human predictions, suggesting that they are able to incorporate information about idiomaticity. We also present an in-depth evaluation of various factors that can affect prediction, such as model and corpus parameters and compositionality operations. General crosslingual analyses reveal the impact of morphological variation and corpus size in the ability of the model to predict compositionality, and of a uniform combination of the components for best results.

Item Type: Article
Subjects: P Language and Literature > P Philology. Linguistics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Elements
Date Deposited: 01 Nov 2018 11:49
Last Modified: 19 Jun 2020 17:22
URI: http://repository.essex.ac.uk/id/eprint/22999

Actions (login required)

View Item View Item