PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation
arXiv:1906.11455
Abstract
Chinese word segmentation (CWS) is a fundamental step of Chinese natural language processing. In this paper, we build a new toolkit, named PKUSEG, for multi-domain word segmentation. Unlike existing single-model toolkits, PKUSEG targets multi-domain word segmentation and provides separate models for different domains, such as web, medicine, and tourism. Besides, due to the lack of labeled data in many domains, we propose a domain adaptation paradigm to introduce cross-domain semantic knowledge via a translation system. Through this method, we generate synthetic data using a large amount of unlabeled data in the target domain and then obtain a word segmentation model for the target domain. We also further refine the performance of the default model with the help of synthetic data. Experiments show that PKUSEG achieves high performance on multiple domains. The new toolkit also supports POS tagging and model training to adapt to various application scenarios. The toolkit is now freely and publicly available for the usage of research and industry.
Cited by in corpus (13)
- Semi-Supervised Variational Reasoning for Medical Dialogue Generation
- Detecting Hallucinated Content in Conditional Neural Sequence Generation
- SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task
- Cross-lingual Entity Alignment with Incidental Supervision
- An internet reviews topic hierarchy mining method based on modified continuous renormalization procedure
- Injecting Word Information with Multi-Level Word Adapter for Chinese Spoken Language Understanding
- Lexicon-constrained Copying Network for Chinese Abstractive Summarization
- Analysing State-Backed Propaganda Websites: a New Dataset and Linguistic Study
- Cue-word Driven Neural Response Generation with a Shrinking Vocabulary
- That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memory
- Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making
- A New Clustering neural network for Chinese word segmentation
- HyperText: Endowing FastText with Hyperbolic Geometry