Hostname: page-component-586b7cd67f-t8hqh Total loading time: 0 Render date: 2024-11-23T20:00:52.810Z Has data issue: false hasContentIssue false
  • English
  • Français

Generating natural language descriptions using speaker-dependent information†

Published online by Cambridge University Press:  27 February 2017

THIAGO C. FERREIRA  and
IVANDRÉ PARABONI
THIAGO C. FERREIRA
Affiliation:
Tilburg center for Cognition and Communication, Tilburg UniversityP.O. Box 90135, 5000 LE Tilburg, the Netherlands e-mail: [email protected]
IVANDRÉ PARABONI
Affiliation:
School of Arts, Sciences and Humanities, University of São PauloAv. Arlindo Bettio, 1000 - São Paulo, Brazil e-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

This paper discusses the issue of human variation in natural language referring expression generation. We introduce a model of content selection that takes speaker-dependent information into account to produce descriptions that closely resemble those produced by each individual, as seen in a number of reference corpora. Results show that our speaker-dependent referring expression generation model outperforms alternatives that do not take human variation into account, or which do so less extensively, and suggest that the use of machine-learning methods may be an ideal approach to mimic complex referential behaviour.

Type
Articles
Information
Natural Language Engineering , Volume 23 , Issue 6 , November 2017 , pp. 813 - 834
Copyright
Copyright © Cambridge University Press 2017 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Footnotes

†

This work has been supported by CAPES and FAPESP. The authors are also grateful to the anonymous reviewers for their valuable comments.

References

Anderson, A., Bader, M., Bard, E., Boyle, E., Doherty, G. M., Garrod, S., Isard, S., Kowtko, J., McAllister, J., Miller, J., Sotillo, C., Thompson, H. S., and Weinert, R., 1991. The HCRC map task corpus. Language and Speech 34: 351–66.CrossRefGoogle Scholar
Arts, A., Maes, A., Noordman, L. G. M., and Jansen, C., 2011. Overspecification facilitates object identification. Journal of Pragmatics 43: 361–74.Google Scholar
Bohnet, B. 2007. IS-FBN, IS-FBS, IS-IAC: The adaptation of two classic algorithms for the generation of referring expressions in order to produce expressions like humans do. In Proceedings of the Language Generation and Machine Translation UCNLG+MT Workshop at MT Summit XI. Copenhagen, pp. 84–6.Google Scholar
Bohnet, B. 2008. The fingerprint of human referring expressions and their surface realization with graph transducers. In Proceedings of the 5th International Natural Language Generation Conference (INLG-2008). Association for Computational Linguistics, Salt Fork, USA, pp. 207–10.Google Scholar
Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J., 1984. Classification and Regression Trees. Statistics/Probability Series. Belmont, USA: Wadsworth Publishing Company.Google Scholar
Cortes, C. and Vapnik, V., 1995. Support-vector networks. Machine Learning 20 (3): 273–97.Google Scholar
Dale, R. 1989. Cooking up referring expressions. In Proceedings of the 27th Annual Meeting on Association for Computational Linguistics (ACL '89). Association for Computational Linguistics, Vancouver, Canada, pp. 68–75.Google Scholar
Dale, R. and Haddock, N. J., 1991. Content determination in the generation of referring expressions. Computational Intelligence 7 (4): 252–65.Google Scholar
Dale, R. and Reiter, E., 1995. Computational interpretations of the Gricean maxims in the generation of referring expressions. Cognitive Science 19 (2): 233–63.Google Scholar
Dale, R. and Viethen, J. 2009. Referring expression generation through attribute-based heuristics. In Proceedings of the 12th European Workshop on Natural Language Generation (ENLG-2009). Association for Computational Linguistics, Athens, Greece, pp. 58–65.Google Scholar
Dice, L. R., 1945. Measures of the amount of ecologic association between species. Ecology 26 (3): 297–302.Google Scholar
dos Santos Silva, D., and Paraboni, I., 2015. Generating spatial referring expressions in interactive 3D worlds. Spatial Cognition & Computation 15 (03): 186–225.Google Scholar
Eugenio, B. D., Jordan, P. W., Thomason, R. H., and Moore, J. D., 2000. The agreement process: an empirical investigation of human-human computer-mediated collaborative dialogues. International Journal of Human-Computer Studies 53 (6): 1017–76.Google Scholar
Fabbrizio, G. D., Stent, A. J., and Bangalore, S. 2008. Trainable speaker-based referring expression generation. In Proceedings of the 12th Conference on Computational Natural Language Learning (CoNLL '08). Association for Computational Linguistics, Manchester, UK, pp. 151–8.Google Scholar
Ferreira, T. C., and Paraboni, I. 2014a. Classification-based referring expression generation. In Gelbukh, A. (ed.), Computational Linguistics and Intelligent Text Processing: 15th International Conference, CICLing 2014, vol. 8403, pp. 481–91. Lecture Notes in Artificial Intelligence. Berlin: Springer Verlag.Google Scholar
Ferreira, T. C., and Paraboni, I. 2014b. Referring expression generation: taking speakers’ preferences into account. In Sojka, P., Horák, A., Kopeček, I., and Pala, K. (eds.), Text, Speech and Dialogue: 17th International Conference, TSD 2014, vol. 8655, pp. 539–46. Lecture Notes in Artificial Intelligence. Berlin: Springer Verlag.Google Scholar
Gatt, A. and Belz, A. 2007. The attribute selection for GRE challenge: overview and evaluation results. In Proceedings of the Language Generation and Machine Translation UCNLG+MT Workshop at MT Summit XI. Copenhagen, pp. 75–83.Google Scholar
Gatt, A., Belz, A., and Kow, E. 2008. The TUNA challenge 2008: overview and evaluation results. In Proceedings of the 5th International Natural Language Generation Conference (INLG-2008). Association for Computational Linguistics, Salt Fork, USA, pp. 198–206.Google Scholar
Gatt, A., Belz, A., and Kow, E. 2009. The TUNA challenge 2009: overview and evaluation results. In Proceedings of the 12th European Workshop on Natural Language Generation (ENLG-2009). Association for Computational Linguistics, Athens, Greece, pp. 174–82.Google Scholar
Gatt, A., Krahmer, E., van Gompel, R., and van Deemter, K. 2013. Production of referring expressions: preference trumps discrimination. In The Annual Meeting of the Cognitive Science Society (CogSci-2013). Berlin, Germany, pp. 483–8.Google Scholar
Gatt, A., van der Sluis, I., and van Deemter, K. 2007. Evaluating algorithms for the generation of referring expressions using a balanced corpus. In Proceedings of the 11th European Workshop on Natural Language Generation (ENLG-2007). Association for Computational Linguistics, Schloss Dagstuhl, Germany, pp. 49–56.Google Scholar
Grice, H. P. 1975. Logic and conversation. In Cole, P. and Morgan, J. L. (eds.), Syntax and Semantics: Vol. 3: Speech Acts, pp. 41–58. San Diego, CA: Academic Press.Google Scholar
Gupta, S. and Stent, A. J. 2005. Automatic evaluation of referring expression generation using corpora. In Proceedings of the Corpus Linguistics 1st Workshop on Using Corpora in Natural Language Generation (UCNLG). Birmingham, UK, pp. 1–6.Google Scholar
Hervás, R., Arroyo, J., Francisco, V., Peinado, F., and Gervás, P. 2016. Influence of personal choices on lexical variability in referring expressions. Natural Language Engineering 22 (2): 257–90, DOI 10.1017/S1351324915000182.Google Scholar
Hervás, R., Francisco, V., and Gervás, P., 2013. Assessing the influence of personal preferences on the choice of vocabulary for natural language generation. Information Processing & Management 49 (4): 817–32.Google Scholar
Koolen, R., Krahmer, E., and Theune, M. 2012. Learning preferences for referring expression generation: effects of domain, language and algorithm. In Proceedings of the 7th International Natural Language Generation Conference (INLG-2012). Association for Computational Linguistics, Utica, USA, pp. 3–11.Google Scholar
Krahmer, E. and van Deemter, K., 2012. Computational generation of referring expressions: a survey. Computational Linguistics 38 (1): 173–218.Google Scholar
Krahmer, E., van Erk, S., and Verleg, A., 2003. Graph-based generation of referring expressions. Computational Linguistics 29 (1): 53–72.CrossRefGoogle Scholar
Paladhi, S. and Bandyopadhyay, S. 2008. JU-PTBSGRE: GRE using prefix tree based structure. In Proceedings of the 5th International Natural Language Generation Conference (INLG-2008). Association for Computational Linguistics, Salt Fork, USA, pp. 230–1.Google Scholar
Paraboni, I., Galindo, M. R., and Iacovelli, D. 2016. Stars2: a corpus of object descriptions in a visual domain. In Language Resources and Evaluation, DOI 10.1007/s10579-016-9350-y.Google Scholar
Paraboni, I. and van Deemter, K. 2013. Reference and the facilitation of search in spatial domains. Language, Cognition and Neuroscience, DOI 10.1080/01690965.2013.805796, pp. 1002–17.Google Scholar
Paraboni, I., Yamasaki, A. K., da Silva, A. S. R., and Teixeira, C. V. M. 2014. Generating underspecified descriptions of landmark objects. In Sojka, P., Horák, A., Kopeček, I., and Pala, K. (eds.), Text, Speech and Dialogue: 17th International Conference, TSD 2014, vol. 8655, pp. 76–83. Lecture Notes in Artificial Intelligence. Berlin: Springer Verlag.Google Scholar
Siddharthan, A. and Copestake, A. 2004. Generating referring expressions in open domains. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics, Barcelona, Spain, pp. 407–14.Google Scholar
van Deemter, K., 2002. Generating referring expressions: boolean extensions of the incremental algorithm. Computational Linguistics 28 (1): 37–52.Google Scholar
Viethen, H. A. E. 2011. The Generation of Natural Descriptions: Corpus-based Investigations of Referring Expressions in Visual Domains. PhD Thesis, Macquarie University, Sydney, Australia.Google Scholar
Viethen, J. and Dale, R. 2010. Speaker-dependent variation in content selection for referring expression generation. In Proceedings of the Australasian Language Technology Association Workshop 2010. Melbourne, Australia, pp. 81–9.Google Scholar
Viethen, J. and Dale, R. 2011. GRE3D7: a corpus of distinguishing descriptions for objects in visual scenes. In Proceedings of the UCNLG+Eval: Language Generation and Evaluation Workshop. Association for Computational Linguistics, Edinburgh, Scotland, pp. 12–22.Google Scholar
Viethen, J., Mitchell, M., and Krahmer, E. 2013. Graphs and spatial relations in the generation of referring expressions. In Proceedings of the 14th European Workshop on Natural Language Generation. Association for Computational Linguistics, Sofia, Bulgaria, pp. 72–81.Google Scholar