Abstract. This paper describes the application of the perceptron algorithm to the morphological disambiguation of Turkish text. Turkish has a productive derivational morphology. Du...
This paper investigates the problem of automatic humour recognition, and provides and in-depth analysis of two of the most frequently observed features of humorous text: human-cent...
This paper addresses the problem of real-word spell checking, i.e., the detection and correction of typos that result in real words of the target language. This paper proposes a me...
Abstract. Polarities are used to sanction grammar fragment combination in high level tree-based formalisms such as eXtenssible MetaGrammar (XMG) and polarized unification grammars...
Although the literature contains reports of very high accuracy figures for the recognition of named entities in text, there are still some named entity phenomena that remain probl...
Ambiguous person names are a problem in many forms of written text, including that which is found on the Web. In this paper we explore the use of unsupervised clustering techniques...