Paper: A Stochastic Japanese Morphological Analyzer Using A Forward-DP Backward-A* N-Best Search Algorithm

ACL ID C94-1032
Title A Stochastic Japanese Morphological Analyzer Using A Forward-DP Backward-A* N-Best Search Algorithm
Venue International Conference on Computational Linguistics
Session Main Conference
Year 1994
Authors
  • Masaaki Nagata (NTT Information and Communication Systems Laboratories, Yokosuka Japan)

We present a novel method for segmenting the input sentence into words and assigning parts of speech to the words. It consists of a statistical language model and an efficient two-pa~qs N-best search algorithm. The algorithm does not require delimiters between words. Thus it is suitable for written Japanese. q'he proposed Japanese morphological analyzer achieved 95. l% recall and 94.6% precision for open text when it was trained and tested on the ATI'¢ Corpus.