International Symposium on Chinese Spoken Language Processing (ISCSLP 2002)

Taipei, Taiwan
August 23-24, 2002

Knowledge-Based Sense Pruning Using the HowNet: An Alternative to Word Sense Disambiguation

Kok-Wee Gan, Chi-Yung Wang, Brian Mak

Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, China

Word sense disambiguation (WSD) is one of the basic problems in natural language processing. Traditional WSD methods provide only one meaning for each word in a passage. However, we believe that textual information alone may not be sufficient to determine the exact meaning of each word which may better be resolved when higher-level knowledge becomes available. In this paper, we propose an alternative to WSD that we call "sense pruning". The objective now is to reduce the number of plausible meanings of a word as much as possible so as to reduce the amount of work in later processing. Sense pruning is guided by information derived from HowNet - a recently developed knowledge base.

Two criteria were used for the evaluation: recall rate and complexity reduction (which is the reduction in the number of possible meanings of a sentence). Effect of the length of the analytical window was studied. For a corpus of 103 Chinese passages from Sinica, Taiwan, with an analytical window of nine words, we obtained a recall rate of 94.14% and reduced the number of possible sentence meanings by 65.3%.


Full Paper

Bibliographic reference.  Gan, Kok-Wee / Wang, Chi-Yung / Mak, Brian (2002): "Knowledge-based sense pruning using the hownet: an alternative to word sense disambiguation", In ISCSLP 2002, paper 44.