Learning to Classify Events from Human Needs Category Descriptions

Haibo Ding, Zhe Feng


Abstract
We study the problem of learning an event classifier from human needs category descriptions, which is challenging due to: (1) the use of highly abstract concepts in natural language descriptions, (2) the difficulty of choosing key concepts. To tackle these two challenges, we propose LeaPI, a zero-shot learning method that first automatically generate weak labels by instantiating high-level concepts with prototypical instances and then trains a human needs classifier with the weakly labeled data. To filter noisy concepts, we design a reinforced selection algorithm to choose high-quality concepts for instantiation. Experimental results on the human needs categorization task show that our method outperforms baseline methods, producing substantially better precision.
Anthology ID:
2020.findings-emnlp.421
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4698–4704
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.421
DOI:
10.18653/v1/2020.findings-emnlp.421
Bibkey:
Cite (ACL):
Haibo Ding and Zhe Feng. 2020. Learning to Classify Events from Human Needs Category Descriptions. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4698–4704, Online. Association for Computational Linguistics.
Cite (Informal):
Learning to Classify Events from Human Needs Category Descriptions (Ding & Feng, Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.findings-emnlp.421.pdf
Optional supplementary material:
 2020.findings-emnlp.421.OptionalSupplementaryMaterial.pdf