Most Natural Language Processing (NLP) systems traditionally use a sequential architecture that represents the classical linguistic levels (lexical-morphological, syntactical, semantic, etc.), but they claim for huge and monolithic modules, that make the backtracking among such modules difficult. By using a…

In this paper, a supervised learning system of word sense disambiguation is presented. It is based on conditional maximum entropy models. This system acquires the linguistic knowledge from an annotated corpus and this knowledge is represented in the form of…