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

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.

10 pages plus 1 page appendix, 3 figures, IJCNLP 2017

References in corpus (4)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Natural Language Processing (almost) from Scratch
• Segmental Recurrent Neural Networks
• A New Recurrent Neural CRF for Learning Non-linear Edge Features

Cited by in corpus (16)

• Glyce: Glyph-vectors for Chinese Character Representations
• Dice Loss for Data-imbalanced NLP Tasks
• Interpreting Deep Learning Models in Natural Language Processing: A Review
• Neural Modeling for Named Entities and Morphology (NEMO^2)
• FGN: Fusion Glyph Network for Chinese Named Entity Recognition
• Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter
• ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information
• Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging
• Enhancing Sindhi Word Segmentation using Subword Representation Learning and Position-aware Self-attention
• Multiple Character Embeddings for Chinese Word Segmentation
• Does Chinese BERT Encode Word Structure?
• Segmenting Natural Language Sentences via Lexical Unit Analysis
• Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models
• Augmenting Part-of-speech Tagging with Syntactic Information for Vietnamese and Chinese
• Neural Sequence Segmentation as Determining the Leftmost Segments
• A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder