English

Distinguishing Antonyms and Synonyms in a Pattern-based Neural Network

Computation and Language 2017-01-12 v1

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.

Keywords

Cite

@article{arxiv.1701.02962,
  title  = {Distinguishing Antonyms and Synonyms in a Pattern-based Neural Network},
  author = {Kim Anh Nguyen and Sabine Schulte im Walde and Ngoc Thang Vu},
  journal= {arXiv preprint arXiv:1701.02962},
  year   = {2017}
}

Comments

EACL 2017, 10 pages

R2 v1 2026-06-22T17:47:15.094Z