Elamur Research⌕
☰
home / papers / 2016 / A Multilingual Predicate Matrix

A Multilingual Predicate Matrix

Paper · 2016 · Maddalen Lopez de Lacalle, Egoitz Laparra, Itziar Aldabe et al.

Summary

Major predicate lexicons such as FrameNet, VerbNet, PropBank and WordNet each capture different aspects of predicate meaning. They were built separately, however, and the manually curated SemLink links between them remain incomplete and expensive to maintain. The authors previously addressed this with the Predicate Matrix 1.2, which combines SemLink with mappings induced automatically. Predicates were linked through graph-based WSD and corpus-based cross-annotation, and roles through similar techniques, with precision favoured over recall. That version still covered only English verbs. This paper introduces Predicate Matrix 1.3, which reuses existing links from external resources to projected resources into PropBank or VerbNet. NomBank adds English nominalizations. AnCora resources (AnCoraVerb via AncoraNet, plus AnCora-Nom) bring in Spanish and Catalan verbs and Spanish nouns. The Basque Verb Index, whose predicates link to PropBank and whose roles link to VerbNet, adds Basque. Argument correspondences are assumed to be direct unless a resource specifies otherwise. The outcome is a multilingual, interoperable predicate lexicon meant to support semantic processing, for example SRL in low-resource languages such as Basque and Catalan.

Key points

  • Automatic predicate mappings in version 1.2, evaluated against SemLink, reached these F-scores: WN-VN 85.3, WN-FN 82.4, WN-PB 64.0 and PB-FN 66.2. Role mappings scored 85.9 for VN-FN and 53.2 for PB-FN.
  • Version 1.2 far exceeds SemLink in coverage. WN-VN lexical mappings grow from 7,665 to 10,832. FN-PB role mappings grow from 4,384 to 14,195, and FN-VN role mappings from 6,934 to 14,258.
  • Version 1.3 adds five extensions:
    • English nouns through PB–NomBank
    • Spanish verbs through PB–AnCoraVerb
    • Spanish nouns through AnCoraVerb–AnCora-Nom
    • Catalan verbs through PB–AnCoraVerb
    • Basque verbs through PB/VN–BVI
  • The projection created new word senses for each wordnet: 53 for English, 6,092 for Spanish, 5,182 for Catalan and 855 for Basque.
  • The resource can be downloaded from adimen.si.ehu.es/web/PredicateMatrix. Planned future work is to evaluate it indirectly through cross-lingual SRL.

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

 Institutions

🎓University of the Basque CountryLeioa · Spain62 works · 16,683 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 19,503 worksArtificial Intelligence · 18,805 worksArts and Humanities · 17,959 worksLanguage and Linguistics · 17,789 works

🧭 Topics 1Research subjects and languages the work is about.Multilingual & cross-lingual NLP · 888 works

Cite

Cite as Maddalen Lopez de Lacalle, Egoitz Laparra, Itziar Aldabe and German Rigau. 2016. A Multilingual Predicate Matrix. Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16).

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

@inproceedings{lacalle2016multilingual,
  title = {{A Multilingual Predicate Matrix}},
  author = {Maddalen Lopez {de Lacalle}, Egoitz Laparra, Itziar Aldabe and German Rigau},
  booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)},
  year = {2016},
  doi = {10.63317/2qjtr4fusckk},
  url = {https://doi.org/10.63317/2qjtr4fusckk}
}

References

16 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Agerri, R., Aldabe, I., Laparra, E., Rigau, G., Fokkens, A., Huijgen, P., van Erp, M., Bevia, R. I., Vossen, P., Minard, A.-L., and Magnini, B. (2016). Multilingual event detection using the newsreader pipelines. In Procedings of the 1st Workshop on Cross-Platform Text Mining and Natural Language Pr… find
  2. Baker, C., Fillmore, C., and Lowe, J. (1997). The berkeley framenet project. In COLING/ACL’98, Montreal, Canada.
  3. Bizer, C., Lehmann, J., Kobilarov, G., Auer, S., Becker, C., Cyganiak, R., and Hellmann, S. (2009). Dbpedia-a crystallization point for the web of data. Web Semantics: Science, Services and Agents on the World Wide Web, 7(3):154–165. find
  4. Bollacker, K., Evans, C., Paritosh, P., Sturge, T., and Taylor, J. (2008). Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIGMOD international conference on Management of data, pages 1247–1250. find
  5. ACM. Burchardt, A., Erk, K., and Frank, A. (2005). A WordNet Detour to FrameNet. In Proceedings of the GLDV 2005 GermaNet II Workshop, pages 408–421, Bonn, Germany. Estarrona, A., Aldezabal, I., and Dı́az de Ilarraza, A. (2015). A methodology for the semiautomatic annotation of epec-rolsem, a basque… find
  6. Fellbaum, C. and Baker, C. F. (2013). Comparing and harmonizing different verb classifications in light of a semantic annotation task. Linguistics, 51(4):707–728. C. Fellbaum, editor. (1998). find
  7. WordNet. An Electronic Lexical Database. The MIT Press. Gurevych, I., Eckle-Kohler, J., Hartmann, S., Matuschek, M., Meyer, C. M., and Wirth, C. (2012). Uby: A large-scale unified lexical-semantic resource based on lmf. In Proceedings of EACL, pages 580–590. find
  8. Kipper, K. (2005). VerbNet: A broad-coverage, comprehensive verb lexicon. Ph.D. thesis, University of Pennsylvania. López de Lacalle, M., Laparra, E., and Rigau, G. (2014a). Extending semlink through wordnet mappings. In Proceedings of the 9th Language Resources and Evaluation Conference (LREC2014)… find
  9. Language Resources and Evaluation. Meyers, A., Reeves, R., Macleod, C., Szekely, R., Zielinska, V., Young, B., and Grishman, R. (2004). The nombank project: An interim report. In In Proceedings of the NAACL/HLT Workshop on Frontiers in Corpus Annotation.
  10. Navigli, R. and Ponzetto, S. P. (2010). Babelnet: Building a very large multilingual semantic network. In Proceedings of the 48th annual meeting of ACL, pages 216–225.
  11. Niles, I. and Pease, A. (2001). Towards a standard upper ontology. In Proceedings of the 2nd International Conference on Formal Ontology in Information Systems (FOIS-2001), pages 17–19. find
  12. Chris Welty and Barry Smith, eds. Palmer, M., Gildea, D., and Kingsbury, P. (2005). The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–106, March.
  13. Palmer, M. (2009). Semlink: Linking propbank, verbnet and framenet. In Proceedings of the Generative Lexicon Conference, pages 9–15. find
  14. Segers, R., Rospocher, M., Vossen, P., Laparra, E., Rigau, G., and Minard, A.-L. (2016). The event and implied situation ontology (eso): Application and evaluation. In Proceedings of the 10th Language Resources and Evaluation Conference (LREC2016), Portorož, Slovenia, May 23-28. find
  15. Suchanek, F. M., Kasneci, G., and Weikum, G. (2007). Yago: A Core of Semantic Knowledge. In WWW conference, New York, NY, USA. ACM Press. Taulé, M., Martı́, M. A., and Recasens, M. (2008a). Ancora: Multilevel annotated corpora for catalan and spanish. In LREC. Taulé, M., Martı́, M. A., and Recasen… find
  16. Vossen, P., Rigau, G., Serafini, L., Stouten, P., Irving, F., and Hage, W. R. V. (2014). Newsreader: recording history from daily news streams. In Proceedings of the 9th Language Resources and Evaluation Conference (LREC2014), Reykjavik, Iceland, May 26-31. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/lacalle-2016-multilingual-predicate-matrix/