Siamese Representation Learning for Unsupervised Relation Extraction

TL;DR

This paper introduces a novel Siamese representation learning framework for unsupervised relation extraction that effectively captures hierarchical relational semantics using only positive pairs, outperforming existing contrastive methods.

Contribution

The proposed framework leverages positive pairs exclusively to improve relation representations and preserve hierarchical information, advancing unsupervised relation extraction performance.

Findings

Significantly outperforms state-of-the-art on benchmark datasets.

Effectively preserves hierarchical relational semantics.

Demonstrates robustness across different datasets.

Abstract

Unsupervised relation extraction (URE) aims at discovering underlying relations between named entity pairs from open-domain plain text without prior information on relational distribution. Existing URE models utilizing contrastive learning, which attract positive samples and repulse negative samples to promote better separation, have got decent effect. However, fine-grained relational semantic in relationship makes spurious negative samples, damaging the inherent hierarchical structure and hindering performances. To tackle this problem, we propose Siamese Representation Learning for Unsupervised Relation Extraction -- a novel framework to simply leverage positive pairs to representation learning, possessing the capability to effectively optimize relation representation of instances and retain hierarchical information in relational feature space. Experimental results show that our model significantly advances the state-of-the-art results on two benchmark datasets and detailed analyses demonstrate the effectiveness and robustness of our proposed model on unsupervised relation extraction.