论文信息 - YNU-HPCC at IJCNLP-2017 Task 1: Chinese Grammatical Error Diagnosis Using a Bi-directional LSTM-CRF Model

YNU-HPCC at IJCNLP-2017 Task 1: Chinese Grammatical Error Diagnosis Using a Bi-directional LSTM-CRF Model

Building a system to detect Chinese grammatical errors is a challenge for natural-language processing researchers. As Chinese learners are increasing, developing such a system can help them study Chinese more easily. This paper introduces a bi-directional long short-term memory (BiLSTM) - conditional random field (CRF) model to produce the sequences that indicate an error type for every position of a sentence, since we regard Chinese grammatical error diagnosis (CGED) as a sequence-labeling problem.

[1] Lung-Hao Lee,et al. Overview of NLP-TEA 2016 Shared Task for Chinese Grammatical Error Diagnosis , 2016, NLP-TEA@COLING.

[2] J. Movellan. Tutorial on Hidden Markov Models , 2006 .

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

[4] Eduard H. Hovy,et al. End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF , 2016, ACL.

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

[6] Yoshua Bengio,et al. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[7] Andrew McCallum,et al. An Introduction to Conditional Random Fields , 2010, Found. Trends Mach. Learn..

[8] Hermann Ney,et al. LSTM Neural Networks for Language Modeling , 2012, INTERSPEECH.

[9] Andrew McCallum,et al. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[10] Xuejie Zhang,et al. Chinese Grammatical Error Diagnosis Using Single Word Embedding , 2016, NLP-TEA@COLING.