Mostly-Unsupervised Statistical Segmentation of Japanese Kanji Sequences

Computer Science – Computation and Language

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

22 pages. To appear in Natural Language Engineering

Scientific paper

10.1017/S1351324902002954

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.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Mostly-Unsupervised Statistical Segmentation of Japanese Kanji Sequences does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Mostly-Unsupervised Statistical Segmentation of Japanese Kanji Sequences, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Mostly-Unsupervised Statistical Segmentation of Japanese Kanji Sequences will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-382469

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.