Automatic SemanticRole Annotation for Portuguese

  • Eckhard Bick University of Southern Denmark

Resumo


This paper describes an automatic annotation system for semantic roles, implemented as an independent addon module for syntactically parsed text. The formalism uses handwritten Constraint Grammar (CG) rules to map and disambiguate 40 different semantic roles. As a proofofconcept, an evaluation on treebank data was performed, where the system achieved an average Fscore of 88.6.

Referências

Afonso, Susana, Eckhard Bick, Renato Haber & Diana Santos (2002). Floresta sintá(c)tica: a treebank for Portuguese. In Proceedings of LREC'2002. pp. 1698-1703, Paris: ELRA

Bick, Eckhard (2000). The Parsing System Palavras Automatic Grammatical Analysis of Portuguese in a Constraint Grammar Famework. Aarhus: Aarhus University Press

Bick, Eckhard (2005), Turning Constraint Grammar Data into Running Dependency Treebanks, In: Civit, M. & Kübler, S. & Martí, M. A. (red.), Proceedings of TLT05, Barcelona, pp.19-27

Bick, Eckhard (2006), "Noun Sense Tagging: Semantic Prototype Annotation of a Portuguese Treebank". In: Hajic, J. & Nivre, J. (red.), Proceedings of TLT 2006, Prague, pp.127-138

Dowty, D. (1987). Thematic proto roles and argument selection, Language 67: 547-619.

Fillmore, C. (1968). The case for case, in E. Bach & R. Harms (eds), Universals in linguistic theory, Holt, Rinehart and Winston, New York.

Foley, W. & van Valin, R. (1984). Functional syntax and Universal Grammar, CUP, Cambridge.

Hajicova, E. & J. Panevova & P. Sgall (2000). A Manual for Tectogrammatic Tagging of the PDT. UFAL/CKL Technical Report TR200009, Charles University, Czech Republic

Jackendoff, R. (1972). Semantic interpretation in generative grammar, The MIT Press, Cambridge, Ma.

Karlsson, F., Voutilainen, A., Heikkilä, J. & Antilla, A. (1995). Constraint Grammar: A language-independent system for parsing unrestricted text, Mouton de Gruyter, Berlin.

Palmer M, Kingsbury P, Gildea D. (2005) "The Proposition Bank: An Annotated Corpus of Semantic Roles". Computational Linguistics 31 (1): 71-106

Santos, D. & Cardoso, N. (2007). HAREM, a primeira avaliação conjunta de sistemas de reconhecimento de entidades mencionadas para português: documentação e actas do encontro. Linguateca

Taulé, M. et al. (2005). "Mapping Syntactic Functions into Semantic Roles". In: Proceedings of TLT2005: 185-194
Publicado
30/06/2007
BICK, Eckhard. Automatic SemanticRole Annotation for Portuguese. In: SIMPÓSIO BRASILEIRO DE TECNOLOGIA DA INFORMAÇÃO E DA LINGUAGEM HUMANA (STIL), 5. , 2007, Rio de Janeiro/RJ. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2007 . p. 1713-1716.