Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF

TL;DR

This paper introduces a character-based bidirectional RNN-CRF model for joint Chinese segmentation and POS tagging, achieving state-of-the-art results across multiple datasets with rich contextual character representations.

Contribution

The paper adapts the bidirectional RNN-CRF architecture with novel character vector representations for Chinese, improving joint segmentation and POS tagging accuracy.

Findings

Achieves 94.38 F1-score on CTB5 dataset.

Model is robust across different datasets and genres.

Outperforms previous state-of-the-art methods.

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.