Advertisement

Analysis and Reference Resolution of Bridge Anaphora across Different Text Genres

  • Iris Hendrickx
  • Orphée De Clercq
  • Veronique Hoste
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7099)

Abstract

We discuss bridge relations in Dutch between two textual referents across six different text genres. After briefly presenting the annotation guidelines and inter-annotation agreement results, we conduct an in-depth manual analysis of the different types of bridge relations found in our data sets. This analysis reveals that for all genres bridging references stand mostly in a class relationship, which is exactly the kind of information represented in a WordNet hierarchy. This inspired us to investigate to what extent a standard coreference resolution system for Dutch is capable of resolving bridge relations across different text genres and study the effect of adding semantic features encoding WordNet information. Our results reveal modest improvements when using Dutch WordNet LCS information for all but one genre.

Keywords

coreference resolution bridging Dutch cross-genre WordNet 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bouma, G., Daelemans, W., Hendrickx, I., Hoste, V., Mineur, A.M.: The COREA-project, manual for the annotation of coreference in Dutch texts. Technical report, University Groningen (2007)Google Scholar
  2. 2.
    Clark, H.: Bridging. In: The Conference on Theoretical Issues in NLP, pp. 169–174 (1975)Google Scholar
  3. 3.
    Daelemans, W., Zavrel, J., van der Sloot, K., van den Bosch, A.: TiMBL: Tilburg Memory Based Learner, version 6.3, Reference Guide. Technical Report ILK Research Group Technical Report Series no. 10-01, Tilburg University (2010)Google Scholar
  4. 4.
    Hendrickx, I., Hoste, V., Daelemans, W.: Evaluating Hybrid Versus Data-Driven Coreference Resolution. In: Branco, A. (ed.) DAARC 2007. LNCS (LNAI), vol. 4410, pp. 137–150. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  5. 5.
    Hoste, V.: Optimization Issues in Machine Learning of Coreference Resolution. PhD thesis, Antwerp University (2005)Google Scholar
  6. 6.
    Jiang, J., Conrath, D.: Semantic similarity based on corpus statistics and lexical taxonomy. In: International Conference on Research in Computational Linguistics, Taiwan, vol. 33 (1997)Google Scholar
  7. 7.
    Korzen, I., Buch-Kromann, M.: Anaphoric relations in the copenhagen dependency treebanks. In: Beyond Semantics: Corpus-based Investigations of Pragmatic and Discourse Phenomena. DGfS Workshop, pp. 83–98 (2011)Google Scholar
  8. 8.
    Lin, D.: Automatic retrieval and clustering of similar words. In: 17th International Conference on Computational Linguistics, Montreal, Quebec, Canada, pp. 768–774 (1998)Google Scholar
  9. 9.
    Markert, K., Nissim, M., Modjeska, N.N.: Using the web for nominal anaphora resolution. In: EACL Workshop on the Computational Treatment of Anaphora, pp. 39–46 (2003)Google Scholar
  10. 10.
    Nedoluzhko, A., Mírovský, J., Pajas, P.: The coding scheme for annotating extended nominal coreference and bridging anaphora in the prague dependency treebank. In: LAW III, pp. 108–111. ACL, Suntec (2009)Google Scholar
  11. 11.
    Ng, V.: Supervised Noun Phrase Coreference Research: The First Fifteen Years. In: 48th Annual Meeting of the Association for Computational Linguistics, pp. 1396–1411 (2010)Google Scholar
  12. 12.
    Poesio, M.: Discourse annotation and semantic annotation in the gnome corpus. In: ACL Workshop on Discourse Annotation (2004)Google Scholar
  13. 13.
    Poesio, M., Ishikawa, T., im Walde, S.S., Vieira, R.: Acquiring lexical knowledge for anaphora resolution. In: 3rd Conference on Language Resources and Evaluation (LREC), pp. 1220–1224 (2002)Google Scholar
  14. 14.
    Poesio, M., Mehta, R., Maroudas, A., Hitzeman, J.: Learning to resolve bridging references. In: 42nd Meeting of the Association for Computational Linguistics (ACL 2004), pp. 143–150 (2004)Google Scholar
  15. 15.
    Poesio, M., Vieira, R.: A corpus-based investigation of definite description use. Computational Linguistics 24(2), 183–216 (1998)Google Scholar
  16. 16.
    Poesio, M., Vieira, R., Teufel, S.: Resolving bridging references in unrestricted text. In: ACL Workshop on Robust Anaphora Resolution, pp. 1–6 (1997)Google Scholar
  17. 17.
    Recasens, M.: Coreference: Theory, Annotation, Resolution and Evaluation. PhD thesis, Department of Linguistics, University of Barcelona, Barcelona, Spain (September 2010)Google Scholar
  18. 18.
    Recasens, M., Hovy, E., Marti, M.: Identity, non-identity, and near-identity: Addressing the complexity of coreference. Lingua 121(6), 1138–1152 (2011)CrossRefGoogle Scholar
  19. 19.
    Recasens, M., Hovy, E., Mart, M.A.: A typology of near-identity relations for coreference (NIDENT). In: Seventh Conference on International Language Resources and Evaluation (LREC 2010), ELRA, Valletta, Malta (2010)Google Scholar
  20. 20.
    Recasens, M., Márquez, L., Sapena, E., Martí, M.A., Tauleé, M., Hoste, V., Poesio, M., Versley, Y.: SemEval-2010 Task 1: Coreference resolution in multiple languages. In: 5th International Workshop on Semantic Evaluations (SemEval 2010), Uppsala, Sweden, pp. 1–8 (2010)Google Scholar
  21. 21.
    Resnik, P.: Using Information Content to Evaluate Semantic Similarity in a Taxonomy. In: International Joint Conference on Artificial Intelligence, Montreal, Canada, vol. 14, pp. 448–453 (1995)Google Scholar
  22. 22.
    Schuurman, I., Hoste, V., Monachesi, P.: Interacting Semantic Layers of Annotation in SoNaR, a Reference Corpus of Contemporary Written Dutch. In: LREC 2010, Valletta, Malta, pp. 2471–2477 (2010)Google Scholar
  23. 23.
    Soon, W.M., Ng, H.T., Lim, D.C.Y.: A machine learning approach to coreference resolution of noun phrases. Computational Linguistics 27(4), 521–544 (2001)CrossRefGoogle Scholar
  24. 24.
    Vieira, R., Poesio, M.: An empirically based system for processing definite descriptions. Computational Linguistics 26, 539–593 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Iris Hendrickx
    • 1
  • Orphée De Clercq
    • 2
  • Veronique Hoste
    • 2
    • 3
  1. 1.Centro de Linguística daUniversidade de LisboaLisboaPortugal
  2. 2.LT3, School of Translation StudiesUniversity CollegeGhentBelgium
  3. 3.Faculty of LinguisticsGhent UniversityGhentBelgium

Personalised recommendations