Elamur Research⌕
☰
home / papers / 2010 / Building an Italian FrameNet through Semi-automatic Corpus Analysis

Building an Italian FrameNet through Semi-automatic Corpus Analysis

Summary

The paper tackles a weakness of the classical Berkeley FrameNet workflow: choosing and annotating example sentences depends heavily on lexicographers' intuition. To build an Italian FrameNet, the authors keep Lexical Unit (LU) encoding manual but support it with distributional evidence extracted automatically from the La Repubblica Corpus, which was tagged and then dependency-parsed with DeSR. For each verb they derive the statistical profile of its subcategorization frames, the typical lexical fillers of each slot, and selectional preferences over WordNet top classes obtained via MultiWordNet. All associations are scored with Simple Log-Likelihood, and an extra step tries to detect dot-object (logical polysemy) types. Annotators use these profiles to decide which frame a verb sense evokes and which Frame Element a slot realizes. The paper illustrates this with visual perception verbs such as intravedere, whose meaning shifts toward opinion when its objects are abstract. The results are a valence database, planned for free web release, and an initial lexicon. This offers a corpus-grounded template for FrameNets in new languages and enriches LUs with preference data.

Key points

  • Source data: La Repubblica Corpus (~390 million tokens of newspaper text), processed with the ILC-UniPi Tagger and the DeSR dependency parser (88.6% LAS). The extracted data were stored in a mySQL database.
  • Selectional preferences adapt the Schulte Im Walde (2006) method. Noun frequencies are split across MultiWordNet senses and propagated to 25 top-nodes, with Simple Log-Likelihood association used as the novel scoring step.
  • A dedicated algorithm takes the two most strongly associated semantic classes per slot and estimates whether a potential dot-object A-B class also applies.
  • The initial Italian FrameNet lexicon has 791 annotated sentences covering 6 visual perception verbs and 9 frames (e.g., PERCEPTION_EXPERIENCE, AWARENESS, OPINION, STATEMENT). Annotation was done in the Berkeley FrameNet Desktop.
  • LUs are extended beyond the standard FrameNet format with frame frequencies, prototypical fillers, and LL-ranked semantic types. Semantic types also help separate FEs, for example a con-PP read as Manner, Instrument, or Body Part.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Semantic role labeling

Cite

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{lenci2010building,
  title = {{Building an Italian FrameNet through Semi-automatic Corpus Analysis}},
  author = {Lenci, Alessandro and Johnson, Martina and Lapesa, Gabriella},
  booktitle = {Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)},
  year = {2010},
  doi = {10.63317/23tzuhug55yc},
  url = {https://doi.org/10.63317/23tzuhug55yc}
}

References

22 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Afra Alishahi and Suzanne Stevenson. 2007. A Cognitive Model for the Representation and Acquisition of Verb Selectional Preferences. In Proceedings of the Workshop on Cognitive Aspects of Computational Language Acquisition, pages 41–48, Prague, Czech Republic. find
  2. Marco Baroni, Silvia Bernardini, Federica Comastri, Lorenzo Piccioni, Alessandra Volpi, Guy Aston, and Marco Mazzoleni. 2004. Introducing the ”la Repubblica” corpus: A large, annotated, TEI (XML)-compliant corpus of newspaper Italian. In Proceedings of LREC 2004, pages 1771–1774, Lisboa, Portugal. find
  3. Jon Barwise. 1981. Scenes and Other Situations. The Journal of Philosophy, 78(7):369–397. find
  4. Cristina Bosco, Simonetta Montemagni, Alessandro Mazzei, Vincenzo Lombardo, Felice Dell’Orletta, and Alessandro Lenci. 2009. Evalita ’09 Parsing Task: comparing dependency parsers and treebanks. In Proceedings of EVALITA 2009, Reggio Emilia, Italy. find
  5. Aljoscha Burchardt, Katrin Erk, Anette Frank, Andrea Kowalski, Sebastian Padó, and Manfred Pinkal. 2009. Using FrameNet for the semantic analysis of the German: Annotation, representation, and automation. In H. C. Boas, editor, Multilingual FrameNets in Computational Lexicography: Methods and Appli… find
  6. Benfeng Chen and Pascale Fung. 2004. Automatic construction of an English-Chinese bilingual FrameNet. In Proceedings of Human Language Technology conference/NAACL, pages 29–32, Boston, MA. find
  7. Renaat Declerck. 1981. On the role of progressive aspect in nonfinite perception verb complements. Glossa, 15:83–114. find
  8. Stefan Evert. 2008. Corpora and collocations. In A. Lüdeling and M. Kytö, editors, Corpus Linguistics. An International Handbook, chapter 58. Mouton de Gruyter, Berlin. find
  9. Charles J. Fillmore and Beryl T. (Sue) Atkins. 1992. Towards a frame-based lexicon: The semantics of RISK and its neighbors. In A. Lehrer and E.F. Kittay, editors, Frames, fields and contrasts, pages 75–102. Lawrence Erlbaum Associates, Hillsdale, NJ. find
  10. Charles J. Fillmore, Miriam R. L. Petruck, Josef Ruppenhofer, and Abby Wright. 2003. FrameNet in action: The case of attaching. International Journal of Lexicography, 16(3):297–332. find
  11. Charles J. Fillmore. 1982. Frame Semantics. In Linguistics in the Morning Calm: Selected Papers from SICOL 1981, pages 111–137. Hanshin, Seoul. find
  12. Charles J. Fillmore. 1985. Frames and the semantics of understanding. Quaderni di semantica, 6:222–254. find
  13. Maria Teresa Guasti. 1993. Causative and perception verbs: A comparative study. Rosenberg & Sellier, Turin, Italy. find
  14. Patrick Hanks and James Pustejovsky. 2005. A pattern dictionary for natural language processing. Revue Française de linguistique appliquée, 10(2):63–82. find
  15. James Higginbotham. 1983. The Logic of Perceptual Reports: An Extensional Alternative to Situation Semantics. The Journal of Philosophy, 80(2):100–127. find
  16. Robert S. Kirsner and Sandra A. Thompson. 1976. The role of pragmatic inference in semantics: a study of sensory verb complements in English. Glossa, 10:200–240. find
  17. Kyoko Hirose Ohara. 2008. Lexicon, Grammar and Multilinguality in the Japanese FrameNet. In Proceedings of LREC 2008, pages 3264–3268, Marrakech, Morocco. find
  18. Emanuele Pianta, Luisa Bentivogli, and Christian Girardi. 2002. MultiWordNet: developing an aligned multilingual database. In Proceedings of the First International Conference on Global WordNet, pages 293–302, Mysore, India. find
  19. James Pustejovsky. 2005. A Survey of Dot Objects. Technical report. Brandeis University. find
  20. Sabine Schulte Im Walde. 2006. Experiments on the automatic induction of german semantic verb classes. Computational Linguistics, 32(2):159–194. find our card
  21. Carlos Subirats. 2009. Spanish FrameNet: A frame-semantic analysis of the Spanish lexicon. In H. C. Boas, editor, Multilingual FrameNets in Computational Lexicography: Methods and Applications, pages 135–162. Mouton de Gruyter, New York. find
  22. Sara Tonelli, Daniele Pighin, Claudio Giuliano, and Emanuele Pianta. 2009. Semi-automatic Development of FrameNet for Italian. In Proceedings of the FrameNet Workshop and Masterclass, Milano, Italy. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/lenci-2010-building-italian-framenet-through-semi/