A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder
arXiv:1906.12035
Abstract
Multi-criteria Chinese word segmentation (MCCWS) aims to exploit the relations among the multiple heterogeneous segmentation criteria and further improve the performance of each single criterion. Previous work usually regards MCCWS as different tasks, which are learned together under the multi-task learning framework. In this paper, we propose a concise but effective unified model for MCCWS, which is fully-shared for all the criteria. By leveraging the powerful ability of the Transformer encoder, the proposed unified model can segment Chinese text according to a unique criterion-token indicating the output criterion. Besides, the proposed unified model can segment both simplified and traditional Chinese and has an excellent transfer capability. Experiments on eight datasets with different criteria show that our model outperforms our single-criterion baseline model and other multi-criteria models. Source codes of this paper are available on Github https://github.com/acphile/MCCWS.
arXiv commentFindings of EMNLP 2020
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Pre-trained Models for Natural Language Processing: A Survey
- Layer Normalization
- Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF
- Toward Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning
- Neural Word Segmentation Learning for Chinese
- Exploring Segment Representations for Neural Segmentation Models
- Unified Multi-Criteria Chinese Word Segmentation with BERT
- State-of-the-art Chinese Word Segmentation with Bi-LSTMs
- Switch-LSTMs for Multi-Criteria Chinese Word Segmentation