We propose a novel unsupervised approach for distinguishing literal and non-literal use of idiomatic expressions. Our model combines an unsupervised and a supervised classifier. T...
We present several unsupervised statistical models for the prepositional phrase attachment task that approach the accuracy of the best supervised methods for this task. Our unsupe...
In the presence of environmental noise, speakers tend to adjust their speech production in an effort to preserve intelligible communication. The noise-induced speech adjustments, c...
We propose a unified manifold learning framework for semi-supervised and unsupervised dimension reduction by employing a simple but effective linear regression function to map the ...
Feiping Nie, Dong Xu, Ivor Wai-Hung Tsang, Changsh...
The purpose of extractive document summarization is to automatically select a number of indicative sentences, passages, or paragraphs from the original document according to a tar...
Shih-Hsiang Lin, Yi-Ting Chen, Hsin-Min Wang, Bin ...