Task demands and individual variation in referring expressions

Adriana-Alexandra Baltaretu, Thiago Castro Ferreira

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

Aiming to improve the human-likeness of natural language generation systems, this study investigates different sources of variation that might influence the production of referring expressions (REs), namely the effect of task demands and inter- intra- individual variation. We collected REs using a discrimination game and varied the instructions, telling speakers that they would get points for being fast, creative, clear, or no incentive would be mentioned. Our results show that task demands affected REs production (number of words, number of attributes), and we observe a considerable amount of variation among the length of REs produced by single speakers, as well as among the REs of different speakers referring to the same targets.
Original languageEnglish
Title of host publicationProceedings of the 9th International Natural Language Generation conference
Place of PublicationEdinburgh, UK
PublisherAssociation for Computational Linguistics (ACL)
Pages89-93
Number of pages5
Publication statusPublished - Sep 2016
EventInternational Conference on Natural Language Generation 2016 - Edinburgh, United Kingdom
Duration: 5 Sep 20168 Sep 2016
Conference number: 9
http://www.macs.hw.ac.uk/InteractionLab/INLG2016/

Conference

ConferenceInternational Conference on Natural Language Generation 2016
Abbreviated titleINLG 2016
CountryUnited Kingdom
CityEdinburgh
Period5/09/168/09/16
Internet address

Cite this

Baltaretu, A-A., & Castro Ferreira, T. (2016). Task demands and individual variation in referring expressions. In Proceedings of the 9th International Natural Language Generation conference (pp. 89-93). Edinburgh, UK: Association for Computational Linguistics (ACL).
Baltaretu, Adriana-Alexandra ; Castro Ferreira, Thiago. / Task demands and individual variation in referring expressions. Proceedings of the 9th International Natural Language Generation conference. Edinburgh, UK : Association for Computational Linguistics (ACL), 2016. pp. 89-93
@inproceedings{012db79f2e3f4ce4a278c15d9f69c8aa,
title = "Task demands and individual variation in referring expressions",
abstract = "Aiming to improve the human-likeness of natural language generation systems, this study investigates different sources of variation that might influence the production of referring expressions (REs), namely the effect of task demands and inter- intra- individual variation. We collected REs using a discrimination game and varied the instructions, telling speakers that they would get points for being fast, creative, clear, or no incentive would be mentioned. Our results show that task demands affected REs production (number of words, number of attributes), and we observe a considerable amount of variation among the length of REs produced by single speakers, as well as among the REs of different speakers referring to the same targets.",
author = "Adriana-Alexandra Baltaretu and {Castro Ferreira}, Thiago",
year = "2016",
month = "9",
language = "English",
pages = "89--93",
booktitle = "Proceedings of the 9th International Natural Language Generation conference",
publisher = "Association for Computational Linguistics (ACL)",

}

Baltaretu, A-A & Castro Ferreira, T 2016, Task demands and individual variation in referring expressions. in Proceedings of the 9th International Natural Language Generation conference. Association for Computational Linguistics (ACL), Edinburgh, UK, pp. 89-93, International Conference on Natural Language Generation 2016, Edinburgh, United Kingdom, 5/09/16.

Task demands and individual variation in referring expressions. / Baltaretu, Adriana-Alexandra; Castro Ferreira, Thiago.

Proceedings of the 9th International Natural Language Generation conference. Edinburgh, UK : Association for Computational Linguistics (ACL), 2016. p. 89-93.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

TY - GEN

T1 - Task demands and individual variation in referring expressions

AU - Baltaretu, Adriana-Alexandra

AU - Castro Ferreira, Thiago

PY - 2016/9

Y1 - 2016/9

N2 - Aiming to improve the human-likeness of natural language generation systems, this study investigates different sources of variation that might influence the production of referring expressions (REs), namely the effect of task demands and inter- intra- individual variation. We collected REs using a discrimination game and varied the instructions, telling speakers that they would get points for being fast, creative, clear, or no incentive would be mentioned. Our results show that task demands affected REs production (number of words, number of attributes), and we observe a considerable amount of variation among the length of REs produced by single speakers, as well as among the REs of different speakers referring to the same targets.

AB - Aiming to improve the human-likeness of natural language generation systems, this study investigates different sources of variation that might influence the production of referring expressions (REs), namely the effect of task demands and inter- intra- individual variation. We collected REs using a discrimination game and varied the instructions, telling speakers that they would get points for being fast, creative, clear, or no incentive would be mentioned. Our results show that task demands affected REs production (number of words, number of attributes), and we observe a considerable amount of variation among the length of REs produced by single speakers, as well as among the REs of different speakers referring to the same targets.

M3 - Conference contribution

SP - 89

EP - 93

BT - Proceedings of the 9th International Natural Language Generation conference

PB - Association for Computational Linguistics (ACL)

CY - Edinburgh, UK

ER -

Baltaretu A-A, Castro Ferreira T. Task demands and individual variation in referring expressions. In Proceedings of the 9th International Natural Language Generation conference. Edinburgh, UK: Association for Computational Linguistics (ACL). 2016. p. 89-93