Elamur Research⌕
☰
home / papers / 2009 / New Features for FrameNet - WordNet Mapping

New Features for FrameNet - WordNet Mapping

Summary

FrameNet offers rich frame-semantic annotation, but its coverage is limited. Many lexical units (LUs) have only a dictionary-style definition and no example sentences, and some frames contain just one or two LUs. Tonelli and Pighin address this by linking FrameNet LUs to WordNet synsets automatically. They train a single Support Vector Machine (SVM) on a small set of manually annotated LU–synset pairs, rather than one classifier per frame. Its compact feature set draws on information earlier work mostly ignored, chiefly stem overlap between the LU definition and the synset gloss, plus WordNet domain labels. Because the method does not need example sentences or large frames, it also works for poorly documented LUs. The resulting mapping, MapNet, reaches about 0.79 precision. The authors then use it to add LUs to English FrameNet, to populate an Italian FrameNet through MultiWordNet, and to label the MultiSemCor parallel corpus with frames. This shows that a cheap supervised mapping can substantially reduce the manual effort of building FrameNet-like resources, including for new languages.

Key points

  • Mapping scale: MapNet considers 33,698 candidate LU–synset pairs, covering 9,120 of 10,100 FrameNet v1.3 LUs, and keeps 5,162 mapped pairs at roughly 0.79 precision.
  • English FrameNet extension: The method adds 4,265 new LUs to 521 frames, enlarging the resource by almost 42%. A manual check of 100 new LUs found 78% correct.
  • Italian frame population: Using MultiWordNet, the method induces 6,429 Italian LUs for 561 frames. In an evaluation of 15 frames containing 191 LUs, 88% were correct.
  • MultiSemCor annotation: Across 12,843 parallel sentences, the method produces 27,793 English and 23,872 Italian frame-labelled instances. On 200 sampled sentences per side, 75% of English and 70% of Italian labels were correct.
  • Future work: The gold standard for training came from De Cao and Basili. The authors plan to add syntactic features and to extend the mapping to other MultiWordNet languages: Spanish, Portuguese, Hebrew and Romanian.

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

Cited by

24 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 21 not yet.

Cite

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

@inproceedings{tonelli2009new,
  title = {{New Features for FrameNet - WordNet Mapping}},
  author = {Tonelli, Sara and Pighin, Daniele},
  booktitle = {Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL-2009)},
  year = {2009},
  url = {https://aclanthology.org/W09-1127/}
}

References

24 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. The Berkeley FrameNet Project. In Proceedings of the 36th ACL Meeting and 17th ICCL Conference. Morgan Kaufmann. find our card
  2. Collin F. Baker, Michael Ellsworth, and Katrin Erk. 2007. SemEval-2007 Task 10: Frame Semantic Structure Extraction. In Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007), pages 99–104, Prague, CZ, June. find
  3. Luisa Bentivogli and Emanuele Pianta. 2005. Exploiting Parallel Texts in the Creation of Multilingual Semantically Annotated Resources: The MultiSemCor Corpus. Natural Language Engineering, Special Issue on Parallel Texts, 11(03):247–261, September. find
  4. Hans C. Boas. 2005. Semantic frames as interlingual representations for multilingual lexical databases. International Journal of Lexicography, 18(4):445–478. find
  5. Aljoscha Burchardt, Katrin Erk, and Annette Frank. 2005. A WordNet detour to FrameNet. In B. Fisseni, H. Schmitz, B. Schröder, and P. Wagner, editors, Sprachtechnologie, mobile Kommunikation und lingis-tische Resourcen, Frankfurt am Main, Germany. Peter Lang. find
  6. Aljoscha Burchardt, Nils Reiter, Stefan Thater, and Annette Frank. 2007. A semantic approach to textual entailment: System evaluation and task analysis. In Proceedings of Pascal RTE-3 Challenge, Prague, CZ. find
  7. Diego De Cao, Danilo Croce, Marco Pennacchiotti, and Roberto Basili. 2008. Combining Word Sense and Usage for modeling Frame Semantics. In Proceedings of STEP 2008, Venice, Italy. find our card
  8. Mario Crespo and Paul Buitelaar. 2008. Domain-specific English-to-Spanish Translation of FrameNet. In Proc. of LREC 2008, Marrakech. find
  9. Christiane Fellbaum, editor. 1998. WordNet: An Electronic Lexical Database. MIT Press. find
  10. C.J. Fillmore, C.R. Johnson, and M. R. L. Petruck. 2003. Background to FrameNet. International Journal of Lexicography, 16:235–250, September. find
  11. Ana-Maria Giuglea and Alessandro Moschitti. 2006. Semantic role labeling via FrameNet, VerbNet and Prop-Bank. In Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual ACL meeting, pages 929–936, Morristown, NJ, US. Association for Computational Linguistics… find
  12. Matthew Honnibal and Tobias Hawker. 2005. Identifying FrameNet frames for verbs from a real-text corpus. In Proceedings of Australasian Language Technology Workshop 2005. find
  13. Thorsten Joachims. 1999. Making large-scale support vector machine learning practical. In Bernhard Schölkopf, Christopher J. C. Burges, and Alexander J Smola, editors, Advances in kernel methods: support vector learning, pages 169–184. MIT Press, Cambridge, MA, USA. find
  14. R. Johansson and P. Nugues. 2007. Using WordNet to extend FrameNet coverage. In Proc. of the Workshop on Building Frame-semantic Resources for Scandinavian and Baltic Languages, at NODALIDA, Tartu. find
  15. Bernardo Magnini and Gabriela Cavaglià. 2000. Integrating Subject Field Codes into WordNet. In Proceedings of LREC 2000, pages 1413–1418, Athens, Greece. find our card
  16. Martha Palmer, Daniel Gildea, and Paul Kingsbury. 2005. The Proposition Bank: An Annotated Corpus of Semantic Roles. Computational Linguistics, 31. find our card
  17. Emanuele Pianta, Luisa Bentivogli, and Christian Girardi. 2002. MultiWordNet: developing an aligned multilingual database. In First International Conference on Global WordNet, pages 292–302, Mysore, India. find
  18. Josef Ruppenhofer, Michael Ellsworth, Miriam R.L. Petruck, Christopher R. Johnson, and Jan Scheffczyk. 2006. FrameNet II: Extended Theory and Practice. Available at http://framenet.icsi.berkeley.edu/book/book.html. ↗
  19. Dan Shen and Mirella Lapata. 2007. Using Semantic Roles to Improve Question Answering. In Proceedings of EMNLP and CONLL, pages 12–21, Prague, CZ. find
  20. Lei Shi and Rada Mihalcea. 2004. Open Text Semantic Parsing Using FrameNet and WordNet. In Proceedings of HLT-NAACL 2004. find our card
  21. Lei Shi and Rada Mihalcea. 2005. Putting Pieces Together: Combining FrameNet, VerbNet and WordNet for Robust Semantic Parsing. In Proceedings of CI-CLing 2005, pages 100–111. Springer. find
  22. Sara Tonelli and Emanuele Pianta. 2008. Frame Information Transfer from English to Italian. In European Language Resources Association (ELRA), editor, Proceedings of LREC 2008, Marrakech, Morocco. find
  23. Vladimir N. Vapnik. 1998. Statistical Learning Theory. Wiley-Interscience. find
  24. Piek Vossen, editor. 1998. EuroWordNet: A Multilingual Database with Lexical Semantic Networks. Springer, October. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tonelli-2009-new-features-framenet-wordnet-mapping/