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 language | English |
---|---|
Title of host publication | Proceedings of the 9th International Natural Language Generation conference |
Place of Publication | Edinburgh, UK |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 89-93 |
Number of pages | 5 |
Publication status | Published - Sept 2016 |
Event | International Conference on Natural Language Generation 2016 - Edinburgh, United Kingdom Duration: 5 Sept 2016 → 8 Sept 2016 Conference number: 9 http://www.macs.hw.ac.uk/InteractionLab/INLG2016/ |
Conference
Conference | International Conference on Natural Language Generation 2016 |
---|---|
Abbreviated title | INLG 2016 |
Country/Territory | United Kingdom |
City | Edinburgh |
Period | 5/09/16 → 8/09/16 |
Internet address |