How Fragile is Relation Extraction under Entity Replacements?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yiwei, Hooi, Bryan, Wang, Fei, Cai, Yujun, Liang, Yuxuan, Zhou, Wenxuan, Tang, Jing, Duan, Manjuan, Chen, Muhao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910436924850176
author Wang, Yiwei
Hooi, Bryan
Wang, Fei
Cai, Yujun
Liang, Yuxuan
Zhou, Wenxuan
Tang, Jing
Duan, Manjuan
Chen, Muhao
author_facet Wang, Yiwei
Hooi, Bryan
Wang, Fei
Cai, Yujun
Liang, Yuxuan
Zhou, Wenxuan
Tang, Jing
Duan, Manjuan
Chen, Muhao
contents Relation extraction (RE) aims to extract the relations between entity names from the textual context. In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations reflected by the textual context. However, existing work has found that the RE models memorize the entity name patterns to make RE predictions while ignoring the textual context. This motivates us to raise the question: ``are RE models robust to the entity replacements?'' In this work, we operate the random and type-constrained entity replacements over the RE instances in TACRED and evaluate the state-of-the-art RE models under the entity replacements. We observe the 30\% - 50\% F1 score drops on the state-of-the-art RE models under entity replacements. These results suggest that we need more efforts to develop effective RE models robust to entity replacements. We release the source code at https://github.com/wangywUST/RobustRE.
format Preprint
id arxiv_https___arxiv_org_abs_2305_13551
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle How Fragile is Relation Extraction under Entity Replacements?
Wang, Yiwei
Hooi, Bryan
Wang, Fei
Cai, Yujun
Liang, Yuxuan
Zhou, Wenxuan
Tang, Jing
Duan, Manjuan
Chen, Muhao
Computation and Language
Artificial Intelligence
Relation extraction (RE) aims to extract the relations between entity names from the textual context. In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations reflected by the textual context. However, existing work has found that the RE models memorize the entity name patterns to make RE predictions while ignoring the textual context. This motivates us to raise the question: ``are RE models robust to the entity replacements?'' In this work, we operate the random and type-constrained entity replacements over the RE instances in TACRED and evaluate the state-of-the-art RE models under the entity replacements. We observe the 30\% - 50\% F1 score drops on the state-of-the-art RE models under entity replacements. These results suggest that we need more efforts to develop effective RE models robust to entity replacements. We release the source code at https://github.com/wangywUST/RobustRE.
title How Fragile is Relation Extraction under Entity Replacements?
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2305.13551