Modeling Multi-Granularity Hierarchical Features for Relation Extraction

Xinnian Liang, Shuangzhi Wu, Mu Li, Zhoujun Li


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.
Anthology ID:
2022.naacl-main.375
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5088–5098
Language:
URL:
https://aclanthology.org/2022.naacl-main.375
DOI:
10.18653/v1/2022.naacl-main.375
Bibkey:
Cite (ACL):
Xinnian Liang, Shuangzhi Wu, Mu Li, and Zhoujun Li. 2022. Modeling Multi-Granularity Hierarchical Features for Relation Extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5088–5098, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Modeling Multi-Granularity Hierarchical Features for Relation Extraction (Liang et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.375.pdf
Code
 xnliang98/sms
Data
SemEval-2010 Task 8