NeuralREG: An end-to-end approach to referring expression generation

Thiago Castro Ferreira, Diego Moussallem, Ákos Kádár, Sander Wubben, Emiel Krahmer


Abstract
Traditionally, Referring Expression Generation (REG) models first decide on the form and then on the content of references to discourse entities in text, typically relying on features such as salience and grammatical function. In this paper, we present a new approach (NeuralREG), relying on deep neural networks, which makes decisions about form and content in one go without explicit feature extraction. Using a delexicalized version of the WebNLG corpus, we show that the neural model substantially improves over two strong baselines.
Anthology ID:
P18-1182
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1959–1969
Language:
URL:
https://aclanthology.org/P18-1182
DOI:
10.18653/v1/P18-1182
Bibkey:
Cite (ACL):
Thiago Castro Ferreira, Diego Moussallem, Ákos Kádár, Sander Wubben, and Emiel Krahmer. 2018. NeuralREG: An end-to-end approach to referring expression generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1959–1969, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
NeuralREG: An end-to-end approach to referring expression generation (Castro Ferreira et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1182.pdf
Presentation:
 P18-1182.Presentation.pdf
Video:
 https://vimeo.com/285804944
Code
 ThiagoCF05/NeuralREG
Data
WebNLG