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%.