# Toward Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning

arXiv: https://arxiv.org/abs/1903.04190 · HTML: https://mlsanity.com/paper/1903.04190/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2019.

## Built on by (most cited first, 11 of 11)

- [Dual-View Distilled BERT for Sentence Embedding](https://mlsanity.com/paper/2104.08675/) (2021)
- [That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memory](https://mlsanity.com/paper/2209.02967/) (2022)
- [DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling](https://mlsanity.com/paper/2109.08818/) (2021)
- [Zero-shot hashtag segmentation for multilingual sentiment analysis](https://mlsanity.com/paper/2112.03213/) (2021)
- [GNN-SL: Sequence Labeling Based on Nearest Examples via GNN](https://mlsanity.com/paper/2212.02017/) (2022)
- [Chinese Word Segmentation with Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2201.08975/) (2022)
- [ERAS: Evaluating the Robustness of Chinese NLP Models to Morphological Garden Path Errors](https://mlsanity.com/paper/2410.13057/) (2024)
- [Green CWS: Extreme Distillation and Efficient Decode Method Towards Industrial Application](https://mlsanity.com/paper/2111.09078/) (2021)
- [MuCPAD: A Multi-Domain Chinese Predicate-Argument Dataset](https://mlsanity.com/paper/2205.06703/) (2022)
- [Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data](https://mlsanity.com/paper/2210.17122/) (2022)
- [Mining Word Boundaries from Speech-Text Parallel Data for Cross-domain Chinese Word Segmentation](https://mlsanity.com/paper/2412.09045/) (2024)

## Abstract (arXiv)

The ambiguous annotation criteria lead to divergence of Chinese Word Segmentation (CWS) datasets in various granularities. Multi-criteria Chinese word segmentation aims to capture various annotation criteria among datasets and leverage their common underlying knowledge. In this paper, we propose a domain adaptive segmenter to exploit diverse criteria of various datasets. Our model is based on Bidirectional Encoder Representations from Transformers (BERT), which is responsible for introducing open-domain knowledge. Private and shared projection layers are proposed to capture domain-specific knowledge and common knowledge, respectively. We also optimize computational efficiency via distillation, quantization, and compiler optimization. Experiments show that our segmenter outperforms the previous state of the art (SOTA) models on 10 CWS datasets with superior efficiency.