Lexical Simplification with Neural Ranking

Gustavo Paetzold, Lucia Specia


Abstract
We present a new Lexical Simplification approach that exploits Neural Networks to learn substitutions from the Newsela corpus - a large set of professionally produced simplifications. We extract candidate substitutions by combining the Newsela corpus with a retrofitted context-aware word embeddings model and rank them using a new neural regression model that learns rankings from annotated data. This strategy leads to the highest Accuracy, Precision and F1 scores to date in standard datasets for the task.
Anthology ID:
E17-2006
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
34–40
Language:
URL:
https://aclanthology.org/E17-2006
DOI:
Bibkey:
Cite (ACL):
Gustavo Paetzold and Lucia Specia. 2017. Lexical Simplification with Neural Ranking. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 34–40, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Lexical Simplification with Neural Ranking (Paetzold & Specia, EACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/E17-2006.pdf
Data
Newsela