Elamur Research⌕
☰
home / papers / 2009 / Integrating WordNet and FrameNet using a Knowledge-based Word Sense Disambiguation Algorithm

Integrating WordNet and FrameNet using a Knowledge-based Word Sense Disambiguation Algorithm

Summary

FrameNet offers rich frame-semantic descriptions, but its coverage is small: about 10,000 lexical units (LUs), compared with more than 150,000 words in WordNet. Laparra and Rigau partially align the two resources by linking each FrameNet LU to a WordNet synset. They treat the LUs of a frame as a coherent group of words and disambiguate them together with SSI-Dijkstra. This knowledge-based, graph-driven WSD method repeatedly selects the sense that is closest, by shortest-path distance, to the senses already interpreted. The graph is built from WordNet and eXtended WordNet. Because the original algorithm needs monosemous words as a starting point, it fails on frames that contain only polysemous LUs. The authors therefore design four variants (FSI, ASI, FSP, ASP) that begin from an initial sense guess. The variants outperform both the most-frequent-sense baseline and plain SSI-Dijkstra. The resulting mapping can expand FrameNet's coverage, add frame information to WordNet, and transfer frames to other languages through aligned wordnets.

Key points

  • The knowledge graph contains 99,635 synset nodes and 636,077 edges. It combines WordNet 1.6 relations with eXtended WordNet relations, which were mapped to version 1.6 using automatic WN Mappings.
  • Of the FrameNet LUs, 9,360 (spread over 708 frames) are found in WordNet. About 190 frames (roughly 26%) contain only polysemous LUs, and basic SSI-Dijkstra produces no output for these.
  • On the 195 frames with at least 10 LUs, overall F1 is 0.69 for the WN most-frequent-sense baseline, 0.75 for SSI-Dijkstra, and 0.76 for FSI and ASI. FSI and ASI reach 0.85 on nouns, while FSP does best on verbs with 0.67.
  • On frames with only polysemous LUs, the best overall F1 is 0.55 (ASI), against 0.54 for the baseline.
  • Results appear close to the P/R/F of 0.80/0.79/0.80 reported in earlier work on four frames, although the setups differ. The mapping is released as WordFrameNet. Planned work includes a hybrid approach that applies FSP to verbs while relying on FSI for nouns and adjectives, a comparison with UKB, and mapping frame elements.

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: Word sense disambiguation · Semantic role labeling

Cited by

7 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 4 not yet.

Cite

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

@inproceedings{laparra2009integrating,
  title = {{Integrating WordNet and FrameNet using a Knowledge-based Word Sense Disambiguation Algorithm}},
  author = {Laparra, Egoitz and Rigau, German},
  booktitle = {Proceedings of the International Conference RANLP-2009},
  year = {2009},
  url = {https://aclanthology.org/R09-1039/}
}

References

29 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. E. Agirre and O. L. de la Calle. Publicly available topic signatures for all wordnet nominal senses. In Proceedings of LREC, Lisbon, Portugal, 2004. find
  2. E. Agirre and A. Soroa. Personalizing pagerank for word sense disambiguation. In Proceedings of the 12th conference of the European chapter of the Association for Computational Linguistics (EACL-2009), Athens, Greece, April 2009. Eurpean Association for Computational Linguistics. find
  3. J. Álvez, J. Atserias, J. Carrera, S. Climent, A. Oliver, and G. Rigau. Consistent annotation of eurowordnet with the top concept ontology. In Proceedings of Fourth International WordNet Conference (GWC’08), 2008. find
  4. J. Atserias, L. Villarejo, G. Rigau, E. Agirre, J. Carroll, B. Magnini, and P. Vossen. The meaning multilingual central repository. In Proceedings of GWC, Brno, Czech Republic, 2004. find
  5. C. Baker, M. Ellsworth, and K. Erk. Semeval-2007 task 19: Frame semantic structure extraction. In Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007), pages 99–104, Prague, Czech Republic, June 2007. Association for Computational Linguistics. find our card
  6. C. Baker, C. Fillmore, and J. Lowe. The berkeley framenet project. In COL-ING/ACL’98, Montreal, Canada, 1997. find our card
  7. A. Burchardt, K. Erk, and A. Frank. A WordNet Detour to FrameNet. In Proceedings of the GLDV 2005 GermaNet II Workshop, pages 408–421, Bonn, Germany, 2005. find
  8. D. D. Cao, D. Croce, M. Pennacchiotti, and R. Basili. Combining word sense and usage for modeling frame semantics. In Proceedings of The Symposium on Semantics in Systems for Text Processing (STEP 2008), Venice, Italy, 2008. find our card
  9. M. Cuadros and G. Rigau. Knownet: Building a large net of knowledge from the web. In 22nd International Conference on Computational Linguistics (COLING’08), Manchester, UK, 2008. find
  10. J. Daudé, L. Padró, and G. Rigau. Validation and Tuning of Wordnet Mapping Techniques. In Proceedings of RANLP, Borovets, Bulgaria, 2003. find
  11. K. Erk and S. Pado. A powerful and versatile xml format for representing role-semantic annotation. In Proceedings of LREC-2004, Lisbon, 2004. find
  12. C. Fellbaum, editor. WordNet. An Electronic Lexical Database. The MIT Press, 1998. find
  13. C. J. Fillmore. Frame semantics and the nature of language. In Annals of the New York Academy of Sciences: Conference on the Origin and Development of Language and Speech, volume 280, pages 20–32, New York, 1976. verbs R 0.48 0,44 0,46 0,51 0,46 adjectives R F 0.80 0.80 0,80 0,80 0,80 0,80 0,60 0,60… find
  14. A.-M. Giuglea and A. Moschitti. Semantic role labeling via framenet, verbnet and propbank. In ACL-44: Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics, pages 929–936, Morristown, NJ, USA, 2006.… find
  15. R. Johansson and P. Nugues. Using WordNet to extend FrameNet coverage. In Proceedings of the Workshop on Building Frame-semantic Resources for Scandinavian and Baltic Languages, at NODALIDA, Tartu, Estonia, May 24 2007. find
  16. K. Kipper. VerbNet: A broad-coverage, comprehensive verb lexicon. PhD thesis, University of Pennsylvania, 2005. find
  17. B. Magnini and G. Cavaglià. Integrating subject field codes into wordnet. In Proceedings of LREC, Athens. Greece, 2000. find our card
  18. D. McCarthy, R. Koeling, J. Weeds, and J. Carroll. Finding predominant senses in untagged text. In Proceedings of ACL, pages 280–297, 2004. find our card
  19. R. Mihalcea and D. Moldovan. extended wordnet: Progress report. In Proceedings of NAACL Workshop on WordNet and Other Lexical Resources, Pittsburgh, PA, 2001. find
  20. R. Navigli. Semi-automatic extension of large-scale linguistic knowledge bases. In Proc. of 18th FLAIRS International Conference (FLAIRS), Clearwater Beach, Florida, 2005. find
  21. R. Navigli and P. Velardi. Structural semantic interconnections: a knowledge-based approach to word sense disambiguation. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 27(7):1063–1074, 2005. find
  22. I. Niles and A. Pease. Towards a standard upper ontology. In Proceedings of the 2nd International Conference on Formal Ontology in Information Systems (FOIS-2001), pages 17–19. Chris Welty and Barry Smith, eds, 2001. find
  23. M. Palmer, D. Gildea, and P. Kingsbury. The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–106, March 2005. find our card
  24. M. Pennacchiotti, D. D. Cao, R. Basili, D. Croce, and M. Roth. Automatic induction of FrameNet lexical units. In Proceedings of Empirical Methods in Natural Language Processing (EMNLP), Honolulu, Hawaii, USA, 2008. find our card
  25. D. Shen and M. Lapata. Using semantic roles to improve question answering. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pages 12–21, 2007. find
  26. L. Shi and R. Mihalcea. Putting pieces together: Combining framenet, verbnet and wordnet for robust semantic parsing. In Proceedings of CICLing, Mexico, 2005. find
  27. C. Subirats and M. R. Petruck. Surprise: Spanish framenet! In Proceedings of the International Congress of Linguists, Praga, 2003. find
  28. S. Tonelli and E. Pianta. A novel approach to mapping framenet lexical units to wordnet synsets. In Proceedings of IWCS-8, Tilburg, The Netherlands, 2009. find
  29. S. Tonelli and D. Pighin. New features for framenet - wordnet mapping. In Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL’09), Boulder, CO, USA, 2009. find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/laparra-2009-integrating-wordnet-framenet-knowledge-based/