%0 Generic %1 chiu2015named %A Chiu, Jason P. C. %A Nichols, Eric %D 2015 %K NER %T Named Entity Recognition with Bidirectional LSTM-CNNs %U http://arxiv.org/abs/1511.08308 %X Named entity recognition is a challenging task that has traditionally required large amounts of knowledge in the form of feature engineering and lexicons to achieve high performance. In this paper, we present a novel neural network architecture that automatically detects word- and character-level features using a hybrid bidirectional LSTM and CNN architecture, eliminating the need for most feature engineering. We also propose a novel method of encoding partial lexicon matches in neural networks and compare it to existing exact match approaches. Extensive evaluation shows that, given only tokenized text, publicly available word vectors, and an automatically constructed lexicon from open sources, our system is able to surpass the reported state-of-the-art on the OntoNotes 5.0 dataset by 2.35 F1 points and achieves competitive results on the CoNLL 2003 dataset, rivaling systems that employ heavy feature engineering, proprietary lexicons, and rich entity linking information.

@misc{chiu2015named, abstract = {Named entity recognition is a challenging task that has traditionally required large amounts of knowledge in the form of feature engineering and lexicons to achieve high performance. In this paper, we present a novel neural network architecture that automatically detects word- and character-level features using a hybrid bidirectional LSTM and CNN architecture, eliminating the need for most feature engineering. We also propose a novel method of encoding partial lexicon matches in neural networks and compare it to existing exact match approaches. Extensive evaluation shows that, given only tokenized text, publicly available word vectors, and an automatically constructed lexicon from open sources, our system is able to surpass the reported state-of-the-art on the OntoNotes 5.0 dataset by 2.35 F1 points and achieves competitive results on the CoNLL 2003 dataset, rivaling systems that employ heavy feature engineering, proprietary lexicons, and rich entity linking information.}, added-at = {2016-03-13T22:22:19.000+0100}, author = {Chiu, Jason P. C. and Nichols, Eric}, biburl = {https://www.bibsonomy.org/bibtex/25e09f2cdca08d268f1bef1c5ad61bd34/xuewei4d}, description = {[1511.08308] Named Entity Recognition with Bidirectional LSTM-CNNs}, interhash = {a0c2c449765cdab9c224a31edd3254df}, intrahash = {5e09f2cdca08d268f1bef1c5ad61bd34}, keywords = {NER}, note = {cite arxiv:1511.08308}, timestamp = {2016-03-13T22:22:19.000+0100}, title = {Named Entity Recognition with Bidirectional LSTM-CNNs}, url = {http://arxiv.org/abs/1511.08308}, year = 2015 }