| Title | NLP-enhanced Content Filtering within the POESIA Project |
| Author(s) |
Mark Hepple (1), Neil Ireson (1), Paolo Allegrini (2), Simone Marchi (2), Simonetta Montemagni (2), Jose Maria Gomez Hidalgo (3)
(1) University of Sheffield, Department of Computer Science, Regent Court, 211 Portobello Street, Sheffield, UK; (2) Istituto di Linguistica Computazionale, CNR, Area della Ricerca di Pisa Via Moruzzi 1, 56124 Pisa, Italy; (3) Departamento de Inteligencia Artificial, Universidad Europea de Madrid, 28670, Villaviciosa de Odon, Madrid, Spain |
| Session | P23-W |
| Abstract | This paper introduces the POESIA internet filtering system, which is open-source, and which combines standard filtering methods, such as positive/negative URL lists, with more advanced techniques, such as image processing and NLP-enhanced text filtering. The description here focusses on components providing textual content filtering for three European languages (English, Italian and Spanish), employing NLP methods to enhance performance. We address also the acquisition of language data needed to develop these filters, and the evaluation of the system and its components. |
| Keyword(s) | Internet filtering, text categorisation, web data acquisition |
| Language(s) | English, French, Italian, Spanish |
| Full Paper | 779.pdf |