Statistical NLG for Generating the Content and Form of Referring Expressions

Xiao Li, Kees Jacobus Van Deemter, Chenghua Lin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Downloads (Pure)

Abstract

This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully. The model does not only select attributes and values for referring to a target referent, but also performs Linguistic Realisation, generating an actual Noun Phrase. Our evaluations suggest that the attribute selection aspect of the algorithm exceeds classic REG algorithms, while the Noun Phrases generated are as similar to those in a previously developed corpus as were Noun Phrases produced by a new set of human speakers.
Original languageEnglish
Title of host publicationProceedings of the 11th International Conference on Natural Language Generation
EditorsEmiel Krahmer, Albert Gatt, Martijn Goudbeek
PublisherAssociation for Computational Linguistics (ACL)
Pages482-291
Number of pages10
ISBN (Print)9781948087865
Publication statusPublished - Nov 2018
Event11th International Conference on Natural Language Generation (INLG 2018) - Tilburg University, Tilburg, Netherlands
Duration: 5 Nov 20188 Nov 2018

Conference

Conference11th International Conference on Natural Language Generation (INLG 2018)
CountryNetherlands
CityTilburg
Period5/11/188/11/18

Fingerprint

Linguistics

Cite this

Li, X., Van Deemter, K. J., & Lin, C. (2018). Statistical NLG for Generating the Content and Form of Referring Expressions. In E. Krahmer, A. Gatt, & M. Goudbeek (Eds.), Proceedings of the 11th International Conference on Natural Language Generation (pp. 482-291). Association for Computational Linguistics (ACL).

Statistical NLG for Generating the Content and Form of Referring Expressions. / Li, Xiao; Van Deemter, Kees Jacobus; Lin, Chenghua.

Proceedings of the 11th International Conference on Natural Language Generation. ed. / Emiel Krahmer; Albert Gatt; Martijn Goudbeek. Association for Computational Linguistics (ACL), 2018. p. 482-291.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, X, Van Deemter, KJ & Lin, C 2018, Statistical NLG for Generating the Content and Form of Referring Expressions. in E Krahmer, A Gatt & M Goudbeek (eds), Proceedings of the 11th International Conference on Natural Language Generation. Association for Computational Linguistics (ACL), pp. 482-291, 11th International Conference on Natural Language Generation (INLG 2018) , Tilburg, Netherlands, 5/11/18.
Li X, Van Deemter KJ, Lin C. Statistical NLG for Generating the Content and Form of Referring Expressions. In Krahmer E, Gatt A, Goudbeek M, editors, Proceedings of the 11th International Conference on Natural Language Generation. Association for Computational Linguistics (ACL). 2018. p. 482-291
Li, Xiao ; Van Deemter, Kees Jacobus ; Lin, Chenghua. / Statistical NLG for Generating the Content and Form of Referring Expressions. Proceedings of the 11th International Conference on Natural Language Generation. editor / Emiel Krahmer ; Albert Gatt ; Martijn Goudbeek. Association for Computational Linguistics (ACL), 2018. pp. 482-291
@inproceedings{8454c1b1425f48aea7d20da226464f83,
title = "Statistical NLG for Generating the Content and Form of Referring Expressions",
abstract = "This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully. The model does not only select attributes and values for referring to a target referent, but also performs Linguistic Realisation, generating an actual Noun Phrase. Our evaluations suggest that the attribute selection aspect of the algorithm exceeds classic REG algorithms, while the Noun Phrases generated are as similar to those in a previously developed corpus as were Noun Phrases produced by a new set of human speakers.",
author = "Xiao Li and {Van Deemter}, {Kees Jacobus} and Chenghua Lin",
note = "Acknowledgments We gratefully acknowledge the anonymous reviewers for their very helpful comments.",
year = "2018",
month = "11",
language = "English",
isbn = "9781948087865",
pages = "482--291",
editor = "Emiel Krahmer and Albert Gatt and Martijn Goudbeek",
booktitle = "Proceedings of the 11th International Conference on Natural Language Generation",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Statistical NLG for Generating the Content and Form of Referring Expressions

AU - Li, Xiao

AU - Van Deemter, Kees Jacobus

AU - Lin, Chenghua

N1 - Acknowledgments We gratefully acknowledge the anonymous reviewers for their very helpful comments.

PY - 2018/11

Y1 - 2018/11

N2 - This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully. The model does not only select attributes and values for referring to a target referent, but also performs Linguistic Realisation, generating an actual Noun Phrase. Our evaluations suggest that the attribute selection aspect of the algorithm exceeds classic REG algorithms, while the Noun Phrases generated are as similar to those in a previously developed corpus as were Noun Phrases produced by a new set of human speakers.

AB - This paper argues that a new generic approach to statistical NLG can be made to perform Referring Expression Generation (REG) successfully. The model does not only select attributes and values for referring to a target referent, but also performs Linguistic Realisation, generating an actual Noun Phrase. Our evaluations suggest that the attribute selection aspect of the algorithm exceeds classic REG algorithms, while the Noun Phrases generated are as similar to those in a previously developed corpus as were Noun Phrases produced by a new set of human speakers.

M3 - Conference contribution

SN - 9781948087865

SP - 482

EP - 291

BT - Proceedings of the 11th International Conference on Natural Language Generation

A2 - Krahmer, Emiel

A2 - Gatt, Albert

A2 - Goudbeek, Martijn

PB - Association for Computational Linguistics (ACL)

ER -