论文信息 - SRCB Entity Discovery and Linking (EDL) and Event Nugget Systems for TAC 2017

SRCB Entity Discovery and Linking (EDL) and Event Nugget Systems for TAC 2017

The SRCB team participated in Entity Discovery and Linking task and Event Nugget Detection task in TAC Knowledge Base Population (KBP) 2017. The EDL system includes English and Chinese entity discovery, candidate generation, entity linking and NIL cluster. The Event Nugget Detection system identifies event nugget mentions and puts them into co-reference chains. We develop event nugget system based in English and Chinese.

[1] Eric Nichols,et al. Named Entity Recognition with Bidirectional LSTM-CNNs , 2015, TACL.

[2] Jürgen Schmidhuber,et al. Long Short-Term Memory , 1997, Neural Computation.

[3] Petr Sojka,et al. Software Framework for Topic Modelling with Large Corpora , 2010 .

[4] Guillaume Lample,et al. Neural Architectures for Named Entity Recognition , 2016, NAACL.

[5] Victor Guimar. Boosting Named Entity Recognition with Neural Character Embeddings , 2015 .

[6] Jason Weston,et al. Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[7] Wei Xu,et al. Bidirectional LSTM-CRF Models for Sequence Tagging , 2015, ArXiv.

[8] Jing Lu,et al. UTD’s Event Nugget Detection and Coreference System at KBP 2017 , 2017, TAC.

[9] Geoffrey E. Hinton,et al. Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[10] Dongyan Zhao,et al. WIP Event Detection System at TAC KBP 2016 Event Nugget Track , 2015, TAC.