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

Abstract

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

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Dual Learning for Machine Translation
• Investigating Backtranslation in Neural Machine Translation
• A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction
• Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study
• Multi-Task Neural Models for Translating Between Styles Within and Across Languages

Cited by in corpus (7)

• Improving Readability for Automatic Speech Recognition Transcription
• Improving Grammatical Error Correction with Machine Translation Pairs
• Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding
• Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction
• Pseudo-Bidirectional Decoding for Local Sequence Transduction
• Generating Human Readable Transcript for Automatic Speech Recognition with Pre-trained Language Model
• Comparison of Grammatical Error Correction Using Back-Translation Models