Word sense disambiguation in untagged text based on term weight learning

This paper describes unsupervised learning algorithm for disambiguating verbal word senses using term weight learning. In our method, collocations which characterise every sense are extracted using similarity-based estimation. For the results, term weight learning is performed. Parameters of term weighting are then estimated so as to maximise the collocations which characterise every sense and minimise the other collocations. The results of experiment demonstrate the effectiveness of the method.