META - MultilanguagE Text Analyzer
Pierpaolo Basile, Marco de Gemmis, Anna Lisa Gentile, Leo Iaquinta, Pasquale Lops · CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro) · 2008
Natural Language Processing (NLP) has a significant impact on many relevant Web-based and Semantic Web applications, such as information filtering and retrieval. Tools supporting the development of NLP applications are playing a key role in textbased information access on the Web. In this paper, we present META (MultilanguagE Text Analyzer), a tool for text analysis, designed with the aim of providing a general framework for NLP tasks over different languages. The system implements both basic and advanced NLP functionalities, such as Word Sense Disambiguation. After describing the main ideas behind the architecture of META, we discuss some results about the processing of different corpora in English and Italian. Finally, we show how META has been integrated in a recommender system for content-based information filtering.