Modeling Multi-Granularity Hierarchical Features for Relation Extraction

Anonymous

Paper Link: https://openreview.net/forum?id=l2AhcPIyEs

Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)

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.

Copyright Consent Signature (type Name Or NA If Not Transferrable): Xinnian Liang

Copyright Consent Name And Address: Beihang University, Beijing, China

Presentation Mode: This paper will be presented virtually

Virtual Presentation Timezone: UTC-8