English

Using Distributional Thesaurus Embedding for Co-hyponymy Detection

Computation and Language 2020-02-27 v1

Abstract

Discriminating lexical relations among distributionally similar words has always been a challenge for natural language processing (NLP) community. In this paper, we investigate whether the network embedding of distributional thesaurus can be effectively utilized to detect co-hyponymy relations. By extensive experiments over three benchmark datasets, we show that the vector representation obtained by applying node2vec on distributional thesaurus outperforms the state-of-the-art models for binary classification of co-hyponymy vs. hypernymy, as well as co-hyponymy vs. meronymy, by huge margins.

Keywords

Cite

@article{arxiv.2002.11506,
  title  = {Using Distributional Thesaurus Embedding for Co-hyponymy Detection},
  author = {Abhik Jana and Nikhil Reddy Varimalla and Pawan Goyal},
  journal= {arXiv preprint arXiv:2002.11506},
  year   = {2020}
}

Comments

Accepted in LREC 2020. arXiv admin note: text overlap with arXiv:1802.04609

R2 v1 2026-06-23T13:54:35.612Z