# A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder

## TL;DR

This paper introduces a unified Transformer-based model for multi-criteria Chinese word segmentation that leverages criterion tokens, improving performance across multiple datasets and Chinese scripts with a simple, fully-shared architecture.

## Contribution

The paper proposes a concise, fully-shared Transformer encoder model for MCCWS that effectively handles multiple criteria and Chinese scripts, outperforming previous multi-task approaches.

## Key findings

- Outperforms single-criterion baseline models.
- Effective across simplified and traditional Chinese.
- Demonstrates strong transfer capabilities.

## 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.