Unsupervised Compositionality Prediction of Nominal Compounds

Unsupervised Compositionality Prediction of Nominal Compounds Silvio Cordeiro Federal University of Rio Grande do Sul and Aix Marseille University, CNRS, LIS silvioricardoc@gmail.com Aline Villavicencio University of Essex and Federal University of Rio Grande do Sul alinev@gmail.com Marco Idiart Federal University of Rio Grande do Sul marco.idiart@gmail.com Carlos Ramisch Aix Marseille University, CNRS, LIS carlos.ramisch@lis-lab.fr 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 data sets 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. 1. Introduction It is a universally acknowledged assumption that the meaning of phrases, expressions, or sentences can be determined by the meanings of their parts and by the rules used Submission received: 4 December 2017; revised version received: 22 June 2018; accepted for publication: 8 August 2018. doi:10.1162/COLI a 00341 © 2019 Association for Computational Linguistics Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license Computational Linguistics Volume 45, Number 1 to combine them. Part of the appeal of this principle of compositionality1 is that it implies that a meaning can be assigned even to a new sentence involving an unseen combination of familiar words (Goldberg 2015). Indeed, for natural language processing (NLP), this is an attractive way of linearly deriving the meaning of larger units from their components, performing the semantic interpretation of any text. For representing the meaning of individual words and their combinations in com- putational systems, distributional semantic models (DSMs) have been widely used. DSMs are based on Harris’ distributional hypothesis that the meaning of a word can be inferred from the context in which it occurs (Harris 1954; Firth 1957). In DSMs, words are usually represented as vectors that, to some extent, capture cooccurrence patterns in corpora (Lin 1998; Landauer, Foltz, and Laham 1998; Mikolov et al. 2013; Baroni, Dinu, and Kruszewski 2014). Evaluation of DSMs has focused on obtaining accurate semantic representations for words, and state-of-the-art models are already capable of obtaining a high level of agreement with human judgments for predicting synonymy or similarity between words (Freitag et al. 2005; Camacho-Collados, Pilehvar, and Navigli 2015; Lapesa and Evert 2017) and for modeling syntactic and semantic analogies be- tween word pairs (Mikolov, Yih, and Zweig 2013). These representations for individual words can also be combined to create representations for larger units such as phrases, …

Content truncated to 500 words