The proliferation of digital libraries and the large amount of existing documents raise important issues in efficient handling of documents. Printed texts in documents need to be...
This paper presents a robust invariant descriptor for symbol-based image recognition and retrieval. A modified Hough-based Transform is used to extract parameter space informatio...
This paper presents a new clustering algorithm called DSCBC which is designed to automatically discover word senses for polysemous words. DSCBC is an extension of CBC Clustering [...
Noriko Tomuro, Steven L. Lytinen, Kyoko Kanzaki, H...
Ontologies form the cornerstone of the Semantic Web and are intended to help researchers to analyze and share knowledge, and as more ontologies are being introduced, it is difficu...
Recognizing textual entailment (TE) is a complex task involving knowledge from many different sources. One major source of information in this task is event factuality, since the ...
The work presented in this paper aims to combine Latent Semantic Analysis methodology, common sense and traditional knowledge representation in order to improve the dialogue capab...
Giovanni Pilato, Agnese Augello, Giorgio Vassallo,...
Knowledge-based natural language processing systems learn by reading, i.e., they process texts to extract knowledge. The performance of these systems crucially depends on knowledg...
With the success of blogs as popular information sharing media, searches on blogs have become popular. In the blogosphere, tagging is used as a means of annotating blog entries wi...
Automatic sentence segmentation of spoken language is an important precursor to downstream natural language processing. Previous studies combine lexical and prosodic features, but...
Discriminative training has been a leading factor for improving automatic speech recognition (ASR) performance over the last decade. The traditional discriminative training, howev...