%0 Journal Article %1 ZHENG201759 %A Zheng, Suncong %A Hao, Yuexing %A Lu, Dongyuan %A Bao, Hongyun %A Xu, Jiaming %A Hao, Hongwei %A Xu, Bo %D 2017 %J Neurocomputing %K ace2005 clstm cnn extraction hybrid network neural relation %P 59 - 66 %R https://doi.org/10.1016/j.neucom.2016.12.075 %T Joint entity and relation extraction based on a hybrid neural network %U http://www.sciencedirect.com/science/article/pii/S0925231217301613 %V 257 %X 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.

@article{ZHENG201759, abstract = {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.}, added-at = {2018-07-02T13:19:35.000+0200}, author = {Zheng, Suncong and Hao, Yuexing and Lu, Dongyuan and Bao, Hongyun and Xu, Jiaming and Hao, Hongwei and Xu, Bo}, biburl = {https://www.bibsonomy.org/bibtex/24044616a05379e0b95171a7f1a4610f7/schwemmlein}, description = {Joint entity and relation extraction based on a hybrid neural network - ScienceDirect}, doi = {https://doi.org/10.1016/j.neucom.2016.12.075}, interhash = {29dc00b17eb5ea177c0bfdd37733eb17}, intrahash = {4044616a05379e0b95171a7f1a4610f7}, issn = {0925-2312}, journal = {Neurocomputing}, keywords = {ace2005 clstm cnn extraction hybrid network neural relation}, note = {Machine Learning and Signal Processing for Big Multimedia Analysis}, pages = {59 - 66}, timestamp = {2018-07-02T13:19:35.000+0200}, title = {Joint entity and relation extraction based on a hybrid neural network}, url = {http://www.sciencedirect.com/science/article/pii/S0925231217301613}, volume = 257, year = 2017 }