Relation Extraction as Text Matching: A Scheme for Multi-hop Knowledge Base Question Answering

Li, Ziyan; Ni, Kan; Wang, Haofen; Zhang, Wenqiang

doi:10.1007/978-981-19-8300-9_21

Cited by 1 publication

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The relation extraction (RE) task aims to extract the semantic relation between entities in the text. RE can facilitate a wide range of downstream applications such as knowledge graph construction (Gajendran et al, 2023) and question answering (Li et al, 2022b), having aroused much attention in recent years. Typical RE methods based on pre-trained language models like BERT (Devlin et al, 2018), or RoBERTa .…”

Section: Introductionmentioning

confidence: 99%

Generating Commonsense Counterfactuals for Stable Relation Extraction

Miao,

Li,

Qian

2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Recent studies on counterfactual augmented data have achieved great success in the coarsegrained natural language processing tasks. However, existing methods encounter two major problems when dealing with the finegrained relation extraction tasks. One is that they struggle to accurately identify causal terms under the invariant entity constraint. The other is that they ignore the commonsense constraint.To solve these problems, we propose a novel framework to generate commonsense counterfactuals for stable relation extraction. Specifically, to identify causal terms accurately, we introduce an intervention-based strategy and leverage a constituency parser for correction. To satisfy the commonsense constraint, we introduce the concept knowledge base WordNet and design a bottom-up relation expansion algorithm on it to uncover commonsense relations between entities. We conduct a series of comprehensive evaluations, including the low-resource, out-of-domain, and adversarialattack settings. The results demonstrate that our framework significantly enhances the stability of base relation extraction models 1 .

show abstract

Section: Introductionmentioning

confidence: 99%