Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study

Abstract

Neural sequence-to-sequence (seq2seq) approaches have proven to be successful in grammatical error correction (GEC). Based on the seq2seq framework, we propose a novel fluency boost learning and inference mechanism. Fluency boosting learning generates diverse error-corrected sentence pairs during training, enabling the error correction model to learn how to improve a sentence's fluency from more instances, while fluency boosting inference allows the model to correct a sentence incrementally with multiple inference steps. Combining fluency boost learning and inference with convolutional seq2seq models, our approach achieves the state-of-the-art performance: 75.72 (F_{0.5}) on CoNLL-2014 10 annotation dataset and 62.42 (GLEU) on JFLEG test set respectively, becoming the first GEC system that reaches human-level performance (72.58 for CoNLL and 62.37 for JFLEG) on both of the benchmarks.

arXiv commentSubstantial text overlap with "Fluency Boost Learning and Inference for Neural Grammatical Error Correction" (accepted by ACL 2018)

References in corpus (8)

• Convolutional Sequence to Sequence Learning
• Neural Language Correction with Character-Based Attention
• Compositional Sequence Labeling Models for Error Detection in Learner Writing
• Neural Network Translation Models for Grammatical Error Correction
• Joint Training for Neural Machine Translation Models with Monolingual Data
• Inherent Biases in Reference based Evaluation for Grammatical Error Correction and Text Simplification
• JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction
• There's No Comparison: Reference-less Evaluation Metrics in Grammatical Error Correction

Cited by in corpus (25)

• Formality Style Transfer with Hybrid Textual Annotations
• Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data
• Improving Readability for Automatic Speech Recognition Transcription
• Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewriting
• Weakly Supervised Grammatical Error Correction using Iterative Decoding
• ENCORE: Ensemble Learning using Convolution Neural Machine Translation for Automatic Program Repair
• Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models
• Parallel Iterative Edit Models for Local Sequence Transduction
• Denoising based Sequence-to-Sequence Pre-training for Text Generation
• Recent Trends in the Use of Deep Learning Models for Grammar Error Handling
• Misspelling Correction with Pre-trained Contextual Language Model
• Parallel Data Augmentation for Formality Style Transfer
• Towards Unsupervised Grammatical Error Correction using Statistical Machine Translation with Synthetic Comparable Corpus
• Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding
• Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction
• Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction
• CUNI System for the Building Educational Applications 2019 Shared Task: Grammatical Error Correction
• Cross-Corpora Evaluation and Analysis of Grammatical Error Correction Models --- Is Single-Corpus Evaluation Enough?
• Jointly Learning to Repair Code and Generate Commit Message
• Comparison of Grammatical Error Correction Using Back-Translation Models
• Improvement in Machine Translation with Generative Adversarial Networks
• Corpora Generation for Grammatical Error Correction
• Variation and generality in encoding of syntactic anomaly information in sentence embeddings
• An Alignment-Agnostic Model for Chinese Text Error Correction
• A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction