Bouchard, G;
Saito Stenetorp, P;
Riedel, S;
(2016)
Learning to Generate Textual Data.
In: Su, J and Carreras, X and Duh, K, (eds.)
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.
(pp. pp. 1608-1616).
Association for Computational Linguistics: Stroudsburg, PA, USA.
Preview |
Text
D16-1167.pdf - Published Version Download (285kB) | Preview |
Abstract
To learn text understanding models with millions of parameters one needs massive amounts of data. In this work, we argue that generating data can compensate for this need. While defining generic data generators is dif- ficult, we propose to allow generators to be “weakly” specified in the sense that a set of parameters controls how the data is generated. Consider for example generators where the example templates, grammar, and/or vocabulary is determined by this set of parameters. Instead of manually tuning these parameters, we learn them from the limited training data at our disposal. To achieve this, we derive an efficient algorithm called GENERE that jointly estimates the parameters of the model and the undetermined generation parameters. We illustrate its benefits by learning to solve math exam questions using a highly parametrized sequence-to-sequence neural network.
Type: | Proceedings paper |
---|---|
Title: | Learning to Generate Textual Data |
Event: | EMNLP 2016: Conference on Empirical Methods in Natural Language Processing, 1-5 November 2016, Austin, Texas, USA |
Location: | Austin, US |
Dates: | 01 November 2016 - 05 November 2016 |
ISBN-13: | 9781945626258 |
Open access status: | An open access version is available from UCL Discovery |
Publisher version: | https://aclweb.org/anthology/D/D16/ |
Language: | English |
Additional information: | Copyright © 2016 Association for Computational Linguistics. |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
URI: | https://discovery.ucl.ac.uk/id/eprint/1530876 |
Archive Staff Only
View Item |