BiRRE: Learning Bidirectional Residual Relation Embeddings for Supervised Hypernymy Detection

Chengyu Wang, Xiaofeng He


Abstract
The hypernymy detection task has been addressed under various frameworks. Previously, the design of unsupervised hypernymy scores has been extensively studied. In contrast, supervised classifiers, especially distributional models, leverage the global contexts of terms to make predictions, but are more likely to suffer from “lexical memorization”. In this work, we revisit supervised distributional models for hypernymy detection. Rather than taking embeddings of two terms as classification inputs, we introduce a representation learning framework named Bidirectional Residual Relation Embeddings (BiRRE). In this model, a term pair is represented by a BiRRE vector as features for hypernymy classification, which models the possibility of a term being mapped to another in the embedding space by hypernymy relations. A Latent Projection Model with Negative Regularization (LPMNR) is proposed to simulate how hypernyms and hyponyms are generated by neural language models, and to generate BiRRE vectors based on bidirectional residuals of projections. Experiments verify BiRRE outperforms strong baselines over various evaluation frameworks.
Anthology ID:
2020.acl-main.334
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3630–3640
Language:
URL:
https://aclanthology.org/2020.acl-main.334
DOI:
10.18653/v1/2020.acl-main.334
Bibkey:
Cite (ACL):
Chengyu Wang and Xiaofeng He. 2020. BiRRE: Learning Bidirectional Residual Relation Embeddings for Supervised Hypernymy Detection. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3630–3640, Online. Association for Computational Linguistics.
Cite (Informal):
BiRRE: Learning Bidirectional Residual Relation Embeddings for Supervised Hypernymy Detection (Wang & He, ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.334.pdf
Video:
 http://slideslive.com/38929383