Extracting Relational Triples Based on Graph Recursive Neural Network via Dynamic Feedback Forest Algorithm
This addresses the problem of knowledge graph construction from unstructured text for NLP researchers, presenting a novel integration method rather than an incremental improvement.
The paper tackles the challenge of integrating named entity recognition and relation extraction for relational triple extraction by converting it into a graph labeling problem using dependency parsing and graph recursive neural networks, with a dynamic feedback forest algorithm achieving state-of-the-art results on benchmark datasets like ACE2005 and NYT.
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.