Paraphrasing verbal metonymy through computational methods

TL;DR

This paper explores computational methods to paraphrase verbal metonymy using distributional semantics, evaluating different word vector models and demonstrating promising accuracy and alignment with human judgment.

Contribution

It introduces a novel approach to paraphrasing verbal metonymy using word vectors from the British National Corpus, comparing CBOW and Skip-gram models.

Findings

Skip-gram models outperform CBOW in paraphrasing verbal metonymy.

The model achieves better-than-chance accuracy in identifying paraphrases.

There is a strong correlation (phi=0.61) between model classification and human judgment.

Abstract

Verbal metonymy has received relatively scarce attention in the field of computational linguistics despite the fact that a model to accurately paraphrase metonymy has applications both in academia and the technology sector. The method described in this paper makes use of data from the British National Corpus in order to create word vectors, find instances of verbal metonymy and generate potential paraphrases. Two different ways of creating word vectors are evaluated in this study: Continuous bag of words and Skip-grams. Skip-grams are found to outperform the Continuous bag of words approach. Furthermore, the Skip-gram model is found to operate with better-than-chance accuracy and there is a strong positive relationship (phi coefficient = 0.61) between the model's classification and human judgement of the ranked paraphrases. This study lends credence to the viability of modelling verbal metonymy through computational methods based on distributional semantics.