Mostly-Unsupervised Statistical Segmentation of Japanese Kanji Sequences

TL;DR

This paper introduces a robust, mostly-unsupervised statistical method for segmenting Japanese Kanji sequences that performs comparably or better than existing tools, and supports multiple segmentation granularities.

Contribution

A novel statistical segmentation algorithm for Japanese Kanji sequences that requires no extensive lexicon or pre-segmented data, improving robustness and flexibility.

Findings

Performs comparably or better than state-of-the-art analyzers

Outperforms previous unsupervised methods for Chinese

Supports multiple segmentation granularities

Abstract

Given the lack of word delimiters in written Japanese, word segmentation is generally considered a crucial first step in processing Japanese texts. Typical Japanese segmentation algorithms rely either on a lexicon and syntactic analysis or on pre-segmented data; but these are labor-intensive, and the lexico-syntactic techniques are vulnerable to the unknown word problem. In contrast, we introduce a novel, more robust statistical method utilizing unsegmented training data. Despite its simplicity, the algorithm yields performance on long kanji sequences comparable to and sometimes surpassing that of state-of-the-art morphological analyzers over a variety of error metrics. The algorithm also outperforms another mostly-unsupervised statistical algorithm previously proposed for Chinese. Additionally, we present a two-level annotation scheme for Japanese to incorporate multiple segmentation granularities, and introduce two novel evaluation metrics, both based on the notion of a compatible bracket, that can account for multiple granularities simultaneously.