Abstract
A sub-task of Natural Language Generation (NLG) is the generation of referring expressions (REG). REG algorithms aim to select attributes that unambiguously identify an entity with respect to a set of distractors. Previous work has defined a methodology to evaluate REG algorithms using real life examples with naturally occurring alterations in the properties of referring entities. It has been found that REG algorithms have key parameters tuned to exhibit a large degree of robustness. Using this insight, we present here experiments for learning the order of semantic properties used by a high performing REG algorithm. Presenting experiments on two types of entities (people and organizations) and using different versions of DBpedia (a freely available knowledge base containing information extracted from Wikipedia pages) we found that robustness of the tuned algorithm and its parameters do coincide but more work is needed to learn these parameters from data in a generalizable fashion.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Statistics taken from the DBpedia change log available at http://wiki.dbpedia.org/services-resources/datasets/change-log.
- 2.
These potential REG tasks, but not actual REG tasks. We use the news article to extract naturally co-occurring entities.
- 3.
In DBpedia 2014, there was an average of 30.12 properties per person while in DBpedia 3.6, there was an average of 17.3.
- 4.
Our publicly available implementation: https://github.com/DrDub/Alusivo.
References
Cahill, L., Carroll, J., Evans, R., Paiva, D., Power, R., Scott, D., van Deemter, K.: From rags to riches: exploiting the potential of a flexible generation architecture. In: Proceedings of the 39th Annual Meeting on Association for Computational Linguistics, pp. 106–113. Association for Computational Linguistics (2001)
Dale, R., Reiter, E.: Computational interpretations of the gricean maxims in the generation of referring expressions. Cogn. Sci. 19(2), 233–263 (1995)
van Deemter, K., Gatt, A., van der Sluis, I., Power, R.: Generation of referring expressions: assessing the incremental algorithm. Cogn. Sci. 36(5), 799–836 (2012)
Duboue, P., Domínguez, M., Estrella, P.: Evaluating robustness of referring expression generation algorithms. In: Proceedings of Mexican International Conference on Artificial Intelligence 2015. IEEE Computer Society (2015)
Gatt, A., Belz, A.: Empirical Methods in Natural Language Generation: Data-oriented Methods and Empirical Evaluation. Springer, Heidelberg (2010)
Gatt, A., van der Sluis, I., van Deemter, K.: Evaluating algorithms for the generation of referring expressions using a balanced corpus. In: Proceedings of the Eleventh European Workshop on Natural Language Generation, ENLG 2007, pp. 49–56. Association for Computational Linguistics, Stroudsburg, PA, USA (2007). http://dl.acm.org/citation.cfm?id=1610163.1610172
Krahmer, E., Deemter, K.V.: Computational generation of referring expressions: a survey. Comput. Linguist. 38, 173–218 (2009)
Krahmer, E., Koolen, R., Theune, D.M.: Is it that difficult to find a good preference order for the incremental algorithm? Cogn. Sci. 36(5), 837–841 (2012)
Lassila, O., Swick, R.R., Wide, W., Consortium, W.: Resource description framework (rdf) model and syntax specification (1998)
Lebanon, G., Lafferty, J.: Combining rankings using conditional probability models on permutations. In: Sammut, C., Hoffmann, A. (eds.) Proceedings of the 19th International Conference on Machine Learning. Morgan Kaufmann Publishers, San Francisco, CA (2002)
Lehmann, J., Isele, R., Jakob, M., Jentzsch, A., Kontokostas, D., Mendes, P.N., Hellmann, S., Morsey, M., van Kleef, P., Auer, S., Bizer, C.: DBpedia - a large-scale, multilingual knowledge base extracted from wikipedia. Semant. Web J. 6(2), 167–195 (2015)
Pacheco, F., Duboue, P.A., Domínguez, M.A.: 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, NAACL HLT 2012, pp. 641–645. Association for Computational Linguistics, Stroudsburg, PA, USA (2012). http://dl.acm.org/citation.cfm?id=2382029.2382136
Acknowledgments
The authors would like to thank Annie Ying and the three anonymous reviewers for comments and suggestions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Duboue, P.A., Domínguez, M.A. (2016). Using Robustness to Learn to Order Semantic Properties in Referring Expression Generation. In: Montes y Gómez, M., Escalante, H., Segura, A., Murillo, J. (eds) Advances in Artificial Intelligence - IBERAMIA 2016. IBERAMIA 2016. Lecture Notes in Computer Science(), vol 10022. Springer, Cham. https://doi.org/10.1007/978-3-319-47955-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-47955-2_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-47954-5
Online ISBN: 978-3-319-47955-2
eBook Packages: Computer ScienceComputer Science (R0)