Binary Tree based Chinese Word Segmentation
This addresses a fundamental issue in Chinese language processing, though it appears incremental as it builds on existing methods like sequence tagging.
The paper tackled the granularity mismatch problem in Chinese word segmentation by proposing a binary tree representation and framework, which reduced errors by up to 20% when applied to a state-of-the-art baseline.
Chinese word segmentation is a fundamental task for Chinese language processing. The granularity mismatch problem is the main cause of the errors. This paper showed that the binary tree representation can store outputs with different granularity. A binary tree based framework is also designed to overcome the granularity mismatch problem. There are two steps in this framework, namely tree building and tree pruning. The tree pruning step is specially designed to focus on the granularity problem. Previous work for Chinese word segmentation such as the sequence tagging can be easily employed in this framework. This framework can also provide quantitative error analysis methods. The experiments showed that after using a more sophisticated tree pruning function for a state-of-the-art conditional random field based baseline, the error reduction can be up to 20%.