文章基本信息

标题：Unsupervised Compositionality Prediction of Nominal Compounds
本地全文：下载
作者：Silvio Cordeiro ; Aline Villavicencio ; Marco Idiart 等
期刊名称：Computational Linguistics
印刷版ISSN：0891-2017
电子版ISSN：1530-9312
出版年度：2019
卷号：45
期号：1
页码：1-57
DOI：10.1162/coli_a_00341
语种：English
出版社：MIT Press
摘要：Nominal compounds such asred wineandnut casedisplay 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.