Joint Bootstrapping Machines for High Confidence Relation Extraction

TL;DR

This paper presents BREX, a semi-supervised bootstrapping method for relation extraction that significantly reduces semantic drift and improves accuracy by jointly expanding entities and templates with enhanced confidence measures.

Contribution

BREX introduces a novel joint bootstrapping approach with improved confidence assessment to prevent semantic drift in relation extraction.

Findings

BREX outperforms previous methods with a 0.13 higher F1 score.

It effectively reduces semantic drift in relation extraction.

Experimental results confirm its superior accuracy across four relationships.

Abstract

Semi-supervised bootstrapping techniques for relationship extraction from text iteratively expand a set of initial seed instances. Due to the lack of labeled data, a key challenge in bootstrapping is semantic drift: if a false positive instance is added during an iteration, then all following iterations are contaminated. We introduce BREX, a new bootstrapping method that protects against such contamination by highly effective confidence assessment. This is achieved by using entity and template seeds jointly (as opposed to just one as in previous work), by expanding entities and templates in parallel and in a mutually constraining fashion in each iteration and by introducing higherquality similarity measures for templates. Experimental results show that BREX achieves an F1 that is 0.13 (0.87 vs. 0.74) better than the state of the art for four relationships.