Skip to main content
×
Home

Generating natural language descriptions using speaker-dependent information

  • THIAGO C. FERREIRA (a1) and IVANDRÉ PARABONI (a2)
Abstract
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.

Copyright
Footnotes
Hide All

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

Footnotes
References
Hide All
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.
Arts A., Maes A., Noordman L. G. M., and Jansen C., 2011. Overspecification facilitates object identification. Journal of Pragmatics 43: 361–74.
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.
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.
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.
Cortes C. and Vapnik V., 1995. Support-vector networks. Machine Learning 20 (3): 273–97.
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. 6875.
Dale R. and Haddock N. J., 1991. Content determination in the generation of referring expressions. Computational Intelligence 7 (4): 252–65.
Dale R. and Reiter E., 1995. Computational interpretations of the Gricean maxims in the generation of referring expressions. Cognitive Science 19 (2): 233–63.
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. 5865.
Dice L. R., 1945. Measures of the amount of ecologic association between species. Ecology 26 (3): 297302.
dos Santos Silva D., and Paraboni I., 2015. Generating spatial referring expressions in interactive 3D worlds. Spatial Cognition & Computation 15 (03): 186225.
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.
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.
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.
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.
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. 7583.
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. 198206.
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.
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.
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. 4956.
Grice H. P. 1975. Logic and conversation. In Cole P. and Morgan J. L. (eds.), Syntax and Semantics: Vol. 3: Speech Acts, pp. 4158. San Diego, CA: Academic Press.
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. 16.
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.
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.
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. 311.
Krahmer E. and van Deemter K., 2012. Computational generation of referring expressions: a survey. Computational Linguistics 38 (1): 173218.
Krahmer E., van Erk S., and Verleg A., 2003. Graph-based generation of referring expressions. Computational Linguistics 29 (1): 5372.
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.
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.
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.
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. 7683. Lecture Notes in Artificial Intelligence. Berlin: Springer Verlag.
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.
van Deemter K., 2002. Generating referring expressions: boolean extensions of the incremental algorithm. Computational Linguistics 28 (1): 3752.
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.
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.
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. 1222.
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. 7281.
Recommend this journal

Email your librarian or administrator to recommend adding this journal to your organisation's collection.

Natural Language Engineering
  • ISSN: 1351-3249
  • EISSN: 1469-8110
  • URL: /core/journals/natural-language-engineering
Please enter your name
Please enter a valid email address
Who would you like to send this to? *
×

Metrics

Full text views

Total number of HTML views: 5
Total number of PDF views: 86 *
Loading metrics...

Abstract views

Total abstract views: 425 *
Loading metrics...

* Views captured on Cambridge Core between 27th February 2017 - 18th November 2017. This data will be updated every 24 hours.