BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Ontology Learning for Portuguese - Hugo Gonçalo Oliveira\, Univer
 sity of Coimbra\, Portugal
DTSTART:20091016T110000Z
DTEND:20091016T120000Z
UID:TALK20469@talks.cam.ac.uk
CONTACT:Laura Rimell
DESCRIPTION:Having in mind both the importance that semantic information p
 lays nowadays in natural language processing\, as well as the work involve
 d in creating lexical resources from the scratch\, this research aims the 
 semi-automatic creation of a lexical ontology for Portuguese. \n\nWhile\, 
 for English\, WordNet [1] established as the standard model of a lexical o
 ntology\, for Portuguese\, the few existing similar resources\, created ma
 nually\, are either on earlier stages of development or not publicly avail
 able for download and entire use. Therefore\, as an alternative to manual 
 creation and maintenance of such resources\, the work proposed is concerne
 d with the development of computational tools capable of extracting lexico
 -semantic knowledge from Portuguese textual resources. The knowledge acqui
 red will then be structured into a public domain lexical ontology. \n\nThe
  extraction procedures will be based on the detection of textual patterns 
 that are indicative of lexico-semantic relations between lexical items. Ma
 chine-readable dictionaries (MRDs) will be used as the primary source of k
 nowledge\, since they are already structured around words and their meanin
 gs\, they typically use simple vocabulary\, they were created by experts a
 nd they are the main source of general knowledge. The project PAPEL [2\, 3
 ] has shown the first steps considering the automatic extraction of semant
 ic information from a general Portuguese MRD\, using handcrafted semantic 
 grammars. Therefore\, the results and conclusions obtained in PAPEL will b
 e used as a starting point. However\, this research is also concerned with
  the exploration of other available Portuguese MRDs. \n\nMoreover\, this w
 ork will not be limited by processing dictionaries so\, textual corpora wi
 ll be used as the second source of knowledge\, in order to enrich the the 
 ontology in several more specific domains. Furthermore\, the quality and u
 tility of the resources developed will be assessed. Besides manual evaluat
 ion\, and considering the time needed to perform the latter\, automatic ev
 aluation methodologies will be devised. In the end of this research\, impo
 rtant contributions to Portuguese NLP are expected\, such as a new public 
 domain lexical resource and computational tools capable of learning lexico
 -semantic information from text. \n\n[1] Christiane Fellbaum\, editor (199
 8). WordNet: An Electronic Lexical Database (Language\, Speech\, and Commu
 nication). The MIT Press. \n\n[2] Hugo Gonçalo Oliveira\, Diana Santos\, 
 Paulo Gomes & Nuno Seco. "PAPEL: a dictionary-based lexical ontology for P
 ortuguese". In António Teixeira\, Vera Lúcia Strube de Lima\, Luís Cald
 as de Oliveira & Paulo Quaresma (eds.)\, Computational Processing of the P
 ortuguese Language\, 8th International Conference\, Proceedings (PROPOR 20
 08) Vol. 5190\, (Aveiro\, Portugal\, 2008)\, Springer Verlag\, pp. 31-40 \
 n\n[3] Hugo Gonçalo Oliveira\, Diana Santos & Paulo Gomes "Relations extr
 acted from a Portuguese dictionary: results and first evaluation". In Luí
 s Seabra Lopes\, Nuno Lau\, Pedro Mariano & Luís Rocha (eds.) Local Proce
 edings of 14th Portuguese Conference on Artificial Intelligence (EPIA)\, A
 veiro\, Portugal\, 2009.
LOCATION:SW01\, Computer Laboratory
END:VEVENT
END:VCALENDAR