ACL 2021short11 citations
A Mixture-of-Experts Model for Antonym-Synonym Discrimination
Abstract
Discrimination between antonyms and synonyms is an important and challenging NLP task. Antonyms and synonyms often share the same or similar contexts and thus are hard to make a distinction. This paper proposes two underlying hypotheses and employs the mixture-of-experts framework as a solution. It works on the basis of a divide-and-conquer strategy, where a number of localized experts focus on their own domains (or subspaces) to learn their specialties, and a gating mechanism determines the space partitioning and the expert mixture. Experimental results have shown that our method achieves the state-of-the-art performance on the task.
BibTeX
@inproceedings{xie-zeng-2021-mixture,
title = "A Mixture-of-Experts Model for Antonym-Synonym Discrimination",
author = "Xie, Zhipeng and
Zeng, Nan",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.71/",
doi = "10.18653/v1/2021.acl-short.71",
pages = "558--564"
}