Iterative Edit-Based Unsupervised Sentence Simplification
Full Text: 2020.acl-main.707.pdf
We present a novel iterative, edit-based approach to unsupervised sentence simplification. Our model is guided by a scoring function involving fluency, simplicity, and meaning preservation. Then, we iteratively perform word and phrase-level edits on the complex sentence. Compared with previous approaches, our model does not require a parallel training set, but is more controllable and interpretable. Experiments on Newsela and WikiLarge datasets show that our approach is nearly as effective as state-of-the-art supervised approaches.
Citation
D. Kumar, L. Mou, L. Golab, O. Vechtomova. "Iterative Edit-Based Unsupervised Sentence Simplification". International Conference on Computational Linguistics and the Association for Computational Linguist, pp 7918–7928, July 2020.| Keywords: | |
| Category: | In Conference |
| Web Links: | doi |
| ACL |
BibTeX
@incollection{Kumar+al:ACL20,
author = {Dhruv Kumar and Lili Mou and Lukasz Golab and Olga Vechtomova},
title = {Iterative Edit-Based Unsupervised Sentence Simplification},
Pages = {7918–7928},
booktitle = {International Conference on Computational Linguistics and the
Association for Computational Linguist},
year = 2020,
}Last Updated: March 01, 2021Submitted by Sabina P
