TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Zero-shot Relation Classification	FewRel	IDL	Avg. F1	62.61	# 3
Zero-shot Relation Classification	Wiki-ZSL	IDL	Avg. F1	67.94	# 3

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/improving-discriminative-learning-for-zero/zero-shot-relation-classification-on-fewrel)](https://paperswithcode.com/sota/zero-shot-relation-classification-on-fewrel?p=improving-discriminative-learning-for-zero)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/improving-discriminative-learning-for-zero/zero-shot-relation-classification-on-wiki-zsl)](https://paperswithcode.com/sota/zero-shot-relation-classification-on-wiki-zsl?p=improving-discriminative-learning-for-zero)`

Improving Discriminative Learning for Zero-Shot Relation Extraction

SpaNLP (ACL) 2022 · Van-Hien Tran, Hiroki Ouchi, Taro Watanabe, Yuji Matsumoto ·

Zero-shot relation extraction (ZSRE) aims to predict target relations that cannot be observed during training. While most previous studies have focused on fully supervised relation extraction and achieved considerably high performance, less effort has been made towards ZSRE. This study proposes a new model incorporating discriminative embedding learning for both sentences and semantic relations. In addition, a self-adaptive comparator network is used to judge whether the relationship between a sentence and a relation is consistent. Experimental results on two benchmark datasets showed that the proposed method significantly outperforms the state-of-the-art methods.

PDF Abstract