TY - GEN
T1 - Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF
AU - Shao, Yan
AU - Hardmeier, Christian
AU - Tiedemann, Jörg
AU - Nivre, Joakim
PY - 2017/12/1
Y1 - 2017/12/1
N2 - We present a character-based model for joint segmentation and POS tagging for Chinese. The bidirectional RNN-CRF architecture for general sequence tagging is adapted and applied with novel vector representations of Chinese characters that capture rich contextual information and lower-than-character level features. The proposed model is extensively evaluated and compared with a state-of-the-art tagger respectively on CTB5, CTB9 and UD Chinese. The experimental results indicate that our model is accurate and robust across datasets in different sizes, genres and annotation schemes. We obtain state-of-the-art performance on CTB5, achieving 94.38 F1-score for joint segmentation and POS tagging.
AB - We present a character-based model for joint segmentation and POS tagging for Chinese. The bidirectional RNN-CRF architecture for general sequence tagging is adapted and applied with novel vector representations of Chinese characters that capture rich contextual information and lower-than-character level features. The proposed model is extensively evaluated and compared with a state-of-the-art tagger respectively on CTB5, CTB9 and UD Chinese. The experimental results indicate that our model is accurate and robust across datasets in different sizes, genres and annotation schemes. We obtain state-of-the-art performance on CTB5, achieving 94.38 F1-score for joint segmentation and POS tagging.
KW - Character-based neural tagging
KW - Joint segmentation and POS tagging
KW - BiRNN-CRF
KW - Chinese natural language processing
KW - Contextual character representations
M3 - Article in proceedings
SN - 978-1-948087-00-1
SN - 978-1-948087-00-1
BT - Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
ER -