Iterative Edit-Based Unsupervised Sentence Simplification
2020-06-17ACL 2020Code Available1· sign in to hype
Dhruv Kumar, Lili Mou, Lukasz Golab, Olga Vechtomova
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/ddhruvkr/Edit-Unsup-TSOfficialIn paperpytorch★ 14
Abstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| Newsela | Edit-Unsup-TS | SARI | 30.44 | — | Unverified |
| TurkCorpus | Edit-Unsup-TS | SARI (EASSE>=0.2.1) | 37.85 | — | Unverified |