Journal
NEUROCOMPUTING
Volume 257, Issue -, Pages 59-66Publisher
ELSEVIER SCIENCE BV
DOI: 10.1016/j.neucom.2016.12.075
Keywords
Neural network; Information extraction; Tagging; Classification
Categories
Funding
- National High Technology Research and Development Program of China (863 Program) [2015AA015402]
- Hundred Talents Program of Chinese Academy of Sciences [Y3S4011031]
- National Natural Science Foundation [71402178]
Ask authors/readers for more resources
Entity and relation extraction is a task that combines detecting entity mentions and recognizing entities' semantic relationships from unstructured text. We propose a hybrid neural network model to extract entities and their relationships without any handcrafted features. The hybrid neural network contains a novel bidirectional encoder-decoder LSTM module (BiLSTM-ED) for entity extraction and a CNN module for relation classification. The contextual information of entities obtained in BiLSTM-ED further pass though to CNN module to improve the relation classification. We conduct experiments on the public dataset ACE05 (Automatic Content Extraction program) to verify the effectiveness of our method. The method we proposed achieves the state-of-the-art results on entity and relation extraction task. (C) 2017 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available