Skip to main content
    • Aa
    • Aa

Generating natural language descriptions using speaker-dependent information


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.

Hide All

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

Linked references
Hide All

This list contains references from the content that can be linked to their source. For a full set of references and notes please see the PDF or HTML where available.

R. Dale 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.

R. Dale and J. Viethen 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.

G. D. Fabbrizio , A. J. Stent , and S. Bangalore 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.

T. C. Ferreira , and I. Paraboni 2014a. Classification-based referring expression generation. In A. Gelbukh (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.

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? *


Full text views

Total number of HTML views: 1
Total number of PDF views: 57 *
Loading metrics...

Abstract views

Total abstract views: 281 *
Loading metrics...

* Views captured on Cambridge Core between 27th February 2017 - 22nd August 2017. This data will be updated every 24 hours.