Modeling Multi-Granularity Hierarchical Features for Relation Extraction

TL;DR

This paper introduces a novel hierarchical feature extraction method for relation extraction that relies solely on input sentences, achieving state-of-the-art results without external knowledge.

Contribution

It proposes a new multi-granularity, hierarchical feature modeling approach for relation extraction using only sentence input, outperforming models with external knowledge.

Findings

Significantly outperforms existing models on benchmark datasets.

Effective across different encoders like LSTM and BERT.

Highlights the importance of multi-granularity and hierarchical feature modeling.

Abstract

Relation extraction is a key task in Natural Language Processing (NLP), which aims to extract relations between entity pairs from given texts. Recently, relation extraction (RE) has achieved remarkable progress with the development of deep neural networks. Most existing research focuses on constructing explicit structured features using external knowledge such as knowledge graph and dependency tree. In this paper, we propose a novel method to extract multi-granularity features based solely on the original input sentences. We show that effective structured features can be attained even without external knowledge. Three kinds of features based on the input sentences are fully exploited, which are in entity mention level, segment level, and sentence level. All the three are jointly and hierarchically modeled. We evaluate our method on three public benchmarks: SemEval 2010 Task 8, Tacred, and Tacred Revisited. To verify the effectiveness, we apply our method to different encoders such as LSTM and BERT. Experimental results show that our method significantly outperforms existing state-of-the-art models that even use external knowledge. Extensive analyses demonstrate that the performance of our model is contributed by the capture of multi-granularity features and the model of their hierarchical structure. Code and data are available at \url{https://github.com/xnliang98/sms}.