A Comparison of Neural Models for Word Ordering

Eva Hasler, Felix Stahlberg, Marcus Tomalin, Adrià de Gispert, Bill Byrne


Abstract
We compare several language models for the word-ordering task and propose a new bag-to-sequence neural model based on attention-based sequence-to-sequence models. We evaluate the model on a large German WMT data set where it significantly outperforms existing models. We also describe a novel search strategy for LM-based word ordering and report results on the English Penn Treebank. Our best model setup outperforms prior work both in terms of speed and quality.
Anthology ID:
W17-3531
Volume:
Proceedings of the 10th International Conference on Natural Language Generation
Month:
September
Year:
2017
Address:
Santiago de Compostela, Spain
Editors:
Jose M. Alonso, Alberto Bugarín, Ehud Reiter
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
208–212
Language:
URL:
https://aclanthology.org/W17-3531
DOI:
10.18653/v1/W17-3531
Bibkey:
Cite (ACL):
Eva Hasler, Felix Stahlberg, Marcus Tomalin, Adrià de Gispert, and Bill Byrne. 2017. A Comparison of Neural Models for Word Ordering. In Proceedings of the 10th International Conference on Natural Language Generation, pages 208–212, Santiago de Compostela, Spain. Association for Computational Linguistics.
Cite (Informal):
A Comparison of Neural Models for Word Ordering (Hasler et al., INLG 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/W17-3531.pdf
Code
 ehasler/tensorflow
Data
Penn Treebank