An input information enhanced model for relation extraction

Ming Lei, Heyan Huang, Chong Feng*, Yang Gao, Chao Su

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

11 引用 (Scopus)

摘要

We present a novel end-to-end model to jointly extract semantic relations and argument entities from sentence texts. This model does not require any handcrafted feature set or auxiliary toolkit, and hence it could be easily extended to a wide range of sequence tagging tasks. A new method of using the word morphology feature for relation extraction is studied in this paper. We combine the word morphology feature and the semantic feature to enrich the representing capacity of input vectors. Then, an input information enhanced unit is developed for the bidirectional long short-term memory network (Bi-LSTM) to overcome the information loss caused by the gate operations and the concatenation operations in the LSTM memory unit. A new tagging scheme using uncertain labels and a corresponding objective function are exploited to reduce the interference information from non-entity words. Experiments are performed on three datasets: The New York Times (NYT) and ACE2005 datasets for relation extraction and the SemEval 2010 task 8 dataset for relation classification. The results demonstrate that our model achieves a significant improvement over the state-of-the-art model for relation extraction on the NYT dataset and achieves a competitive performance on the ACE2005 dataset.

源语言英语
页(从-至)9113-9126
页数14
期刊Neural Computing and Applications
31
12
DOI
出版状态已出版 - 1 12月 2019

指纹

探究 'An input information enhanced model for relation extraction' 的科研主题。它们共同构成独一无二的指纹。

引用此

Lei, M., Huang, H., Feng, C., Gao, Y., & Su, C. (2019). An input information enhanced model for relation extraction. Neural Computing and Applications, 31(12), 9113-9126. https://doi.org/10.1007/s00521-019-04430-3