Distinguishing Antonyms and Synonyms in a Pattern-based Neural Network

TL;DR

This paper introduces AntSynNET, a neural network that leverages syntactic patterns and word distance features from parse trees to better distinguish antonyms from synonyms, improving pattern-based NLP classification accuracy.

Contribution

The novel AntSynNET model integrates lexical, syntactic, and distance features from parse trees to enhance antonym and synonym classification.

Findings

AntSynNET outperforms previous pattern-based methods.

Incorporating syntactic path distance improves classification accuracy.

Pattern-based neural networks can effectively differentiate antonyms and synonyms.

Abstract

Distinguishing between antonyms and synonyms is a key task to achieve high performance in NLP systems. While they are notoriously difficult to distinguish by distributional co-occurrence models, pattern-based methods have proven effective to differentiate between the relations. In this paper, we present a novel neural network model AntSynNET that exploits lexico-syntactic patterns from syntactic parse trees. In addition to the lexical and syntactic information, we successfully integrate the distance between the related words along the syntactic path as a new pattern feature. The results from classification experiments show that AntSynNET improves the performance over prior pattern-based methods.