Antonym vs Synonym Distinction using InterlaCed Encoder NETworks (ICE-NET)

TL;DR

This paper introduces ICE-NET, a novel neural network model designed to better distinguish antonym and synonym pairs by capturing relation-specific properties, achieving improved classification performance on benchmark datasets.

Contribution

The paper proposes ICE-NET, a new neural network architecture that models relation-specific properties for antonym and synonym distinction, outperforming existing methods.

Findings

ICE-NET achieves up to 1.8% higher F1-score than previous models.

The model effectively captures relation-specific properties.

Experimental results validate ICE-NET's superior performance.

Abstract

Antonyms vs synonyms distinction is a core challenge in lexico-semantic analysis and automated lexical resource construction. These pairs share a similar distributional context which makes it harder to distinguish them. Leading research in this regard attempts to capture the properties of the relation pairs, i.e., symmetry, transitivity, and trans-transitivity. However, the inability of existing research to appropriately model the relation-specific properties limits their end performance. In this paper, we propose InterlaCed Encoder NETworks (i.e., ICE-NET) for antonym vs synonym distinction, that aim to capture and model the relation-specific properties of the antonyms and synonyms pairs in order to perform the classification task in a performance-enhanced manner. Experimental evaluation using the benchmark datasets shows that ICE-NET outperforms the existing research by a relative score of upto 1.8% in F1-measure. We release the codes for ICE-NET at https://github.com/asif6827/ICENET.