Iterative Edit-Based Unsupervised Sentence Simplification

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.

PDF Abstract ACL 2020 PDF ACL 2020 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text Simplification Newsela Edit-Unsup-TS SARI 30.44 # 5
BLEU 17.36 # 7
Text Simplification TurkCorpus Edit-Unsup-TS SARI (EASSE>=0.2.1) 37.85 # 10
BLEU 73.62 # 11


No methods listed for this paper. Add relevant methods here