Hypernym Detection Using Strict Partial Order Networks

Sarthak Dash, Md. Faisal Mahbub Chowdhury, Alfio Gliozzo, Nandana Mihindukulasooriya, Nicolas Rodolfo Fauceglia

AAAI 2020 pp. 7626-7633

doi:10.1609/AAAI.V34I05.6263 /aaai/2020/dash2020aaai-hypernym/

Abstract

This paper introduces Strict Partial Order Networks (SPON), a novel neural network architecture designed to enforce asymmetry and transitive properties as soft constraints. We apply it to induce hypernymy relations by training with is-a pairs. We also present an augmented variant of SPON that can generalize type information learned for in-vocabulary terms to previously unseen ones. An extensive evaluation over eleven benchmarks across different tasks shows that SPON consistently either outperforms or attains the state of the art on all but one of these benchmarks.

PDF AAAI Semantic Scholar

Cite

Text

Dash et al. "Hypernym Detection Using Strict Partial Order Networks." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I05.6263

Markdown

[Dash et al. "Hypernym Detection Using Strict Partial Order Networks." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/dash2020aaai-hypernym/) doi:10.1609/AAAI.V34I05.6263

BibTeX

@inproceedings{dash2020aaai-hypernym,
  title     = {{Hypernym Detection Using Strict Partial Order Networks}},
  author    = {Dash, Sarthak and Chowdhury, Md. Faisal Mahbub and Gliozzo, Alfio and Mihindukulasooriya, Nandana and Fauceglia, Nicolas Rodolfo},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {7626-7633},
  doi       = {10.1609/AAAI.V34I05.6263},
  url       = {https://mlanthology.org/aaai/2020/dash2020aaai-hypernym/}
}