Abstract
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.
Original language | English |
---|---|
Title of host publication | Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers) |
Publication date | 1 Dec 2017 |
ISBN (Print) | 978-1-948087-00-1, 978-1-948087-00-1 |
Publication status | Published - 1 Dec 2017 |
Externally published | Yes |