We present two machine learning approaches to information extraction from semi-structured documents that can be used if no annotated training data are available, but there does ex...
In any system for Natural Language Processing having a dictionary, the question arises as to whiclh entries are included in it. In this paper, I address the subquestion as to whet...
Corpus-based grammar induction generally relies on hand-parsed training data to learn the structure of the language. Unfortunately, the cost of building large annotated corpora is...
Abstract. Object-oriented language concepts have been highly successful, resulting in a large number of object-oriented languages and language extensions. Unfortunately, formal met...
We propose a robust method of automatically constructing a bilingual word sense dictionary from readily available monolingual ontologies by using estimation-maximization, without ...