Extracting Relational Triples Based on Graph Recursive Neural Network via Dynamic Feedback Forest Algorithm

TL;DR

This paper introduces a novel graph-based approach using recursive neural networks and a dynamic feedback forest algorithm to improve the extraction of relational triples from text, effectively integrating NER and RE subtasks.

Contribution

It proposes converting triple extraction into a graph labeling problem and introduces a dynamic feedback forest algorithm for better subtask integration during training.

Findings

Effective triple extraction demonstrated by experimental results

Improved integration of NER and RE subtasks

Enhanced structural information utilization

Abstract

Extracting relational triples (subject, predicate, object) from text enables the transformation of unstructured text data into structured knowledge. The named entity recognition (NER) and the relation extraction (RE) are two foundational subtasks in this knowledge generation pipeline. The integration of subtasks poses a considerable challenge due to their disparate nature. This paper presents a novel approach that converts the triple extraction task into a graph labeling problem, capitalizing on the structural information of dependency parsing and graph recursive neural networks (GRNNs). To integrate subtasks, this paper proposes a dynamic feedback forest algorithm that connects the representations of subtasks by inference operations during model training. Experimental results demonstrate the effectiveness of the proposed method.