English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We study sequence-to-sequence (seq2seq) pre-training with data augmentationfor sentence rewriting. Instead of training a seq2seq model with gold trainingdata and augmented data simultaneously, we separate them to train in differentphases: pre-training with the augmented data and fine-tuning with the golddata. We also introduce multiple data augmentation methods to help modelpre-training for sentence rewriting. We evaluate our approach in two typicalwell-defined sentence rewriting tasks: Grammatical Error Correction (GEC) andFormality Style Transfer (FST). Experiments demonstrate our approach can betterutilize augmented data without hurting the model's trust in gold data andfurther improve the model's performance with our proposed data augmentationmethods.  Our approach substantially advances the state-of-the-art results inwell-recognized sentence rewriting benchmarks over both GEC and FST.Specifically, it pushes the CoNLL-2014 benchmark's $F_{0.5}$ score and JFLEGTest GLEU score to 62.61 and 63.54 in the restricted training setting, 66.77and 65.22 respectively in the unrestricted setting, and advances GYAFCbenchmark's BLEU to 74.24 (2.23 absolute improvement) in E&M domain and 77.97(2.64 absolute improvement) in F&R domain.

Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewriting