We describe a simple improvement to ngram language models where we estimate the distribution over closed-class (function) words separately from the conditional distribution of ope...
The increased importance of XML as a data representation format has led to several proposals for facilitating the development of applications that operate on XML data. These propo...
Matthew Harren, Mukund Raghavachari, Oded Shmueli,...
Automatic sentence segmentation of spoken language is an important precursor to downstream natural language processing. Previous studies combine lexical and prosodic features, but...
Objectives: To discuss the relationships between ontologies, terminologies and language in the context of Natural Language Processing (NLP) applications in order to show the negat...
Robert H. Baud, Werner Ceusters, Patrick Ruch, Ann...
The increasing amount of available textual information makes necessary the use of Natural Language Processing (NLP) tools. These tools have to be used on large collections of docu...