Skip to main content
SpringerLink
Log in

Data and models for metonymy resolution

  • Published:
Language Resources and Evaluation Aims and scope Submit manuscript

Abstract

We describe the first shared task for figurative language resolution, which was organised within SemEval-2007 and focused on metonymy. The paper motivates the linguistic principles of data sampling and annotation and shows the task’s feasibility via human agreement. The five participating systems mainly used supervised approaches exploiting a variety of features, of which grammatical relations proved to be the most useful. We compare the systems’ performance to automatic baselines as well as to a manually simulated approach based on selectional restriction violations, showing some limitations of this more traditional approach to metonymy recognition. The main problem supervised systems encountered is data sparseness, since metonymies in general tend to occur more rarely than literal uses. Also, within metonymies, the reading distribution is skewed towards a few frequent metonymy types. Future task developments should focus on addressing this issue.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Notes

  1. The example is from the Berkeley Master Metaphor list (http://cogsci.berkeley.edu/lakoff/).

  2. This and all following examples in this paper are from the British National Corpus (BNC) (Burnard 1995). An exception is Ex. 22.

  3. Org-for-members metonymies referring to a spokesperson are quite commonplace so that it is tempting to see them as literal readings. We follow here previous linguistic research (Fass 1997; Lakoff and Johnson 1980) that see these as metonymies.

  4. https://www.cia.gov/cia/publications/factbook/index.html.

  5. FUH results are slightly different from the FUH system paper due to a preprocessing problem in the system, fixed only after the run submission deadline.

  6. This is sometimes enhanced with morphological/syntactic violations such as the plural use for proper names (Copestake and Briscoe 1995) or anaphoric information (Markert and Hahn 2002). However, the basic model relies to a large degree on SRs.

  7. The SUBJ and GRAMM baselines are equal on this subset.

  8. We thank Diana McCarthy for pointing that problem out to us.

References

  • Agirre, E., Màrquez, L., & Wicentowski, R. (Eds.). (2007). Proceedings of the fourth international workshop on semantic evaluations (SemEval-2007). Prague, Czech Republic: Association for Computational Linguistics.

  • Barnden, J., Glasbey, S., Lee, M., & Wallington, A. (2003). Domain-transcending mappings in a system for metaphorical reasoning. In Proc. of EACL-2003, pp. 57–61.

  • Birke, J., & Sarkaar, A. (2006). A clustering approach for the nearly unsupervised recognition of nonliteral language. In Proceedings of EACL-2006.

  • Briscoe, T., & Copestake, A. (1999). Lexical rules in constraint-based grammar. Computational Linguistics, 25(4), 487–526.

    Google Scholar 

  • Burnard, L. (1995). Users’ Reference Guide, British National Corpus. Oxford, England: British National Corpus Consortium.

    Google Scholar 

  • Carletta, J. (1996). Assessing agreement on classification tasks: The kappa statistic. Computational Linguistics, 22(2), 249–254.

    Google Scholar 

  • Clark, S., & Weir, D. (2002). Class-based probability estimation using a semantic hierarchy. Computational Linguistics, 28(2), 187–206.

    Google Scholar 

  • Copestake, A., & Briscoe, T. (1995). Semi-productive polysemy and sense extension. Journal of Semantics, 12, 15–67.

    Article  Google Scholar 

  • Cunningham, H., Maynard, D., Bontcheva, K., & Tablan, V. (2002). GATE: A framework and graphical development environment for robust NLP tools and applications. In Proc. of ACL-2002.

  • Fass, D. (1997). Processing metaphor and metonymy. Stanford, CA: Ablex.

    Google Scholar 

  • Fellbaum, C. (Ed.). (1998). WordNet: An Electronic Lexical Database. Cambridge, MA: MIT Press.

  • Harabagiu, S. (1998). Deriving metonymic coercions from WordNet. In Workshop on the Usage of WordNet in Natural Language Processing Systems, COLING-ACL ’98, Montreal, Canada, pp. 142–148.

  • Hobbs, J. R., Stickel, M. E., Appelt, D. E., & Martin, P. (1993). Interpretation as abduction. Artificial Intelligence, 63, 69–142.

    Article  Google Scholar 

  • Kamei, S.-I., & Wakao, T. (1992). Metonymy: Reassessment, survey of acceptability and its treatment in machine translation systems. In Proc. of ACL-1992, pp. 309–311.

  • Krishnakamuran, S., & Zhu, X. (2007). Hunting elusive metaphors using lexical resources. In Proc. of the NAACL-2007 Workshop on Computational Approaches to Figurative Language.

  • Lakoff, G., & Johnson, M. (1980). Metaphors we live by. Chicago, IL: Chicago University Press.

    Google Scholar 

  • Lapata, M., & Lascarides, A. (2003). A probabilistic account of logical metonymy. Computational Linguistics, 29, 263–317.

    Google Scholar 

  • Leveling, J., & Hartrumpf, S. (2006). On metonymy recognition for gir. In Proc. of GIR-2006.

  • Levin, B. (1993). English verb classes and alternations. Chicago: University of Chicago Press.

  • Markert, K., & Hahn, U. (2002). Understanding metonymies in discourse. Artificial Intelligence, 135(1/2), 145–198.

    Article  Google Scholar 

  • Markert, K., & Nissim, M. (2002). Metonymy resolution as a classification task. In Proc. of EMNLP-2002, pp. 204–213.

  • Markert, K., & Nissim, M. (2006). Metonymic proper names: A corpus-based account. In A. Stefanowitsch (Ed.), Corpora in cognitive linguistics. Vol. 1: Metaphor and metonymy. Berlin: Mouton de Gruyter.

  • Martin, J. (1994). Metabank: A knowledge base of metaphoric language conventions. Computational Intelligence, 10(2), 134–149.

    Article  Google Scholar 

  • Mason, Z. (2004). Cormet: A computational corpus-based conventional metaphor extraction system. Computational Linguistics, 30(1), 23–44.

    Article  Google Scholar 

  • McCarthy, D., & Carroll, J. (2003). Disambiguating nouns, verbs and adjectives using automatically acquired selectional preferences. Computational Linguistics, 29(4), 639–654.

    Article  Google Scholar 

  • Nissim, M., & Markert, K. (2003). Syntactic features and word similarity for supervised metonymy resolution. In Proc. of ACL-2003, pp. 56–63.

  • Nunberg, G. (1995). Transfers of meaning. Journal of Semantics, 12, 109–132.

    Article  Google Scholar 

  • Peirsman, Y. (2006). Example-based metonymy recognition for proper nouns. In Student Session of EACL 2006.

  • Pustejovsky, J. (1995). The generative lexicon. Cambridge, MA: MIT Press.

    Google Scholar 

  • Schuler, K. K. (2005). VerbNet: A broad-coverage, comprehensive verb lexicon. Dissertation, University of Pennsylvania.

  • Stallard, D. (1993). Two kinds of metonymy. In Proc. of ACL-1993, pp. 87–94.

Download references

Acknowledgements

We thank the BNC Consortium for allowing us to distribute the extracted samples. We are also grateful to the annotators for the selectional restriction simulations: Ben Hachey, Tim O’Donnell and especially Stephen Clark, who bore the brunt of the annotation. We also had valuable discussions with Diana McCarthy during the preparation of this work.

Author information

Authors and Affiliations

  1. School of Computing, University of Leeds, Woodhouse Lane, LS2 9JT, Leeds, UK

    Katja Markert

  2. Department of Linguistics and Oriental Studies, University of Bologna, via Zamboni 33, 40126, Bologna, Italy

    Malvina Nissim

Authors
  1. Katja Markert
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Malvina Nissim
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Katja Markert.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Markert, K., Nissim, M. Data and models for metonymy resolution. Lang Resources & Evaluation 43, 123–138 (2009). https://doi.org/10.1007/s10579-009-9087-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10579-009-9087-y

Keywords

Search

Navigation