Abstract. In this article, we propose the use of suffix arrays to efficiently implement n-gram language models with practically unlimited size n. This approach, which is used with ...
In this paper, we introduce a method that automatically builds text classifiers in a new language by training on already labeled data in another language. Our method transfers the...
Psycholinguistic studies suggest a model of human language processing that 1) performs incremental interpretation of spoken utterances or written text, 2) preserves ambiguity by m...
William Schuler, Samir AbdelRahman, Tim Miller, La...
This paper introduces a class of statistical mechanisms, called hidden understanding models, for natural language processing. Much of the framework for hidden understanding models...
Scott Miller, Richard M. Schwartz, Robert J. Bobro...
Probabilistic processes appear naturally in various contexts, with applications to Business Processes, XML data management and more. Many models for specifying and querying such p...