Abstract
In this paper we describe and evaluate an algorithm for generating referring expressions that uses linear regression for learning the probability of using certain properties to describe an object in a given scene. The algorithm we present is an extension of a refinement algorithm modified to take probabilities learnt from corpora into account. As a result, the algorithm is able not only to generate correct referring expressions that uniquely identify the referents but it also generates referring expressions that are considered equal or better than those generated by humans in 92% of the cases by a human judge. We classify and give examples of the referring expressions that humans prefer, and indicate the potential impact of our work for theories of the egocentric use of language.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Altamirano, R., Areces, C., Benotti, L.: Probabilistic refinement algorithms for the generation of referring expressions. In: Proceedings of the 24th International Conference on Computational Linguistics, pp. 53–62 (2012)
Areces, C., Figueira, S., Gorín, D.: Using logic in the generation of referring expressions. In: Pogodalla, S., Prost, J.-P. (eds.) LACL 2011. LNCS, vol. 6736, pp. 17–32. Springer, Heidelberg (2011)
Areces, C., Koller, A., Striegnitz, K.: Referring expressions as formulas of description logic. In: Proceedings of the 5th International Natural Language Generation Conference (INLG 2008), pp. 42–49. Association for Computational Linguistics, Morristown (2008)
Arts, A., Maes, A., Noordman, L., Jansen, C.: Overspecification facilitates object identification. Journal of Pragmatics 43(1), 361–374 (2011)
Baader, F., McGuiness, D., Nardi, D., Patel-Schneider, P. (eds.): The Description Logic Handbook: Theory, implementation and applications. Cambridge University Press (2003)
Dale, R.: Cooking up referring expressions. In: Proceedings of the 27th Annual Meeting on Association for Computational Linguistics, pp. 68–75 (1989)
Dale, R., Reiter, E.: Computational interpretations of the Gricean maxims in the generation of referring expressions. Cognitive Science 19(2), 233–263 (1995)
Engelhardt, P., Bailey, K., Ferreira, F.: Do speakers and listeners observe the gricean maxim of quantity? Journal of Memory and Language 54(4), 554–573 (2006)
Gargett, A., Garoufi, K., Koller, A., Striegnitz, K.: The GIVE-2 corpus of giving instructions in virtual environments. In: Proceedings of the 7th International Conference on Language Resources and Evaluation (LREC), Malta (2010)
Gatt, A., Belz, A., Kow, E.: The TUNA challenge 2008: Overview and evaluation results. In: Proceedings of the 5th International Conference on Natural Language Generation, pp. 198–206. Association for Computational Linguistics (2008)
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. ACM SIGKDD Explorations Newsletter 11(1), 10–18 (2009)
Keysar, B., Barr, D.J., Horton, W.S.: The Egocentric Basis of Language Use. Current Directions in Psychological Science 7(2), 46–49 (1998)
Krahmer, E.J., Theune, M., Viethen, J., Hendrickx, I.: Graph: The costs of redundancy in referring expressions. In: Proceedings of the 5th International Natural Language Generation Conference, Salt Fork, Ohio, USA, pp. 227–229. The Association for Computational Linguistics, USA (2008)
de Lucena, D.J., Paraboni, I.: USP-EACH frequency-based greedy attribute selection for referring expressions generation. In: Proceedings of the 5th International Conference on Natural Language Generation (INLG 2008), pp. 219–220. Association for Computational Linguistics (2008)
Pacheco, F., Duboue, P., Domínguez, M.: On the feasibility of open domain referring expression generation using large scale folksonomies. In: Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 641–645. Association for Computational Linguistics, Montréal (2012)
Paige, R., Tarjan, R.: Three partition refinement algorithms. SIAM Journal on Computing 16(6), 973–989 (1987)
Passonneau, R.: Measuring agreement on set-valued items (masi) for semantic and pragmatic annotation. In: Proceedings of the International Conference on Language Resources and Evaluation, LREC (2006)
Reiter, E., Dale, R.: Building Natural Language Generation Systems. Cambridge University Press, Cambridge (2000)
Ruud, K., Emiel, K., Mariët, T.: Learning preferences for referring expression generation: Effects of domain, language and algorithm. In: INLG 2012 Proceedings of the Seventh International Natural Language Generation Conference, pp. 3–11. Association for Computational Linguistics, Utica (2012)
Viethen, H.A.E.: The Generation of Natural Descriptions: Corpus-Based Investigations of Referring Expressions in Visual Domains. Ph.D. thesis, Macquarie University, Sydney, Australia (2011)
Winograd, T.: Understanding natural language. Cognitive Psychology 3(1), 1–191 (1972)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Benotti, L., Altamirano, R. (2013). Evaluation of a Refinement Algorithm for the Generation of Referring Expressions. In: Brézillon, P., Blackburn, P., Dapoigny, R. (eds) Modeling and Using Context. CONTEXT 2013. Lecture Notes in Computer Science(), vol 8175. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40972-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-40972-1_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40971-4
Online ISBN: 978-3-642-40972-1
eBook Packages: Computer ScienceComputer Science (R0)