Lampouras, G. and Vlachos, A. orcid.org/0000-0003-2123-5071 (2016) Imitation learning for language generation from unaligned data. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. 26th International Conference on Computational Linguistics, 11/12/2016 - 17/12/2016, Osaka. The COLING 2016 Organizing Committee , pp. 1101-1112. ISBN 978-4-87974-702-0
Abstract
Natural language generation (NLG) is the task of generating natural language from a meaning representation. Rule-based approaches require domain-specific and manually constructed linguistic resources, while most corpus based approaches rely on aligned training data and/or phrase templates. The latter are needed to restrict the search space for the structured prediction task defined by the unaligned datasets. In this work we propose the use of imitation learning for structured prediction which learns an incremental model that handles the large search space while avoiding explicitly enumerating it. We adapted the Locally Optimal Learning to Search (Chang et al., 2015) framework which allows us to train against non-decomposable loss functions such as the BLEU or ROUGE scores while not assuming gold standard alignments. We evaluate our approach on three datasets using both automatic measures and human judgements and achieve results comparable to the state-of-the-art approaches developed for each of them. Furthermore, we performed an analysis of the datasets which examines common issues with NLG evaluation.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © The Authors 2016. This work is licenced under a Creative Commons Attribution 4.0 International Licence. Licence details: http:// creativecommons.org/licenses/by/4.0/ |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Funding Information: | Funder Grant number ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL (EPSRC) EP/M005429/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 25 Jan 2017 09:53 |
Last Modified: | 25 Jan 2017 10:11 |
Status: | Published |
Publisher: | The COLING 2016 Organizing Committee |
Refereed: | Yes |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:111166 |