Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction

Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills. However, existing GEC models tend to produce spurious corrections or fail to detect lots of errors. The quality estimation model is necessary to ensure learners get accurate GEC results and avoid misleading from poorly corrected sentences. Well-trained GEC models can generate several high-quality hypotheses through decoding, such as beam search, which provide valuable GEC evidence and can be used to evaluate GEC quality. However, existing models neglect the possible GEC evidence from different hypotheses. This paper presents the Neural Verification Network (VERNet) for GEC quality estimation with multiple hypotheses. VERNet establishes interactions among hypotheses with a reasoning graph and conducts two kinds of attention mechanisms to propagate GEC evidence to verify the quality of generated hypotheses. Our experiments on four GEC datasets show that VERNet achieves state-of-the-art grammatical error detection performance, achieves the best quality estimation results, and significantly improves GEC performance by reranking hypotheses. All data and source codes are available at https://github.com/thunlp/VERNet.

[1]  Raymond Hendy Susanto,et al.  The CoNLL-2014 Shared Task on Grammatical Error Correction , 2014 .

[2]  Marcin Junczys-Dowmunt,et al.  Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data , 2019, BEA@ACL.

[3]  Hwee Tou Ng,et al.  Better Evaluation for Grammatical Error Correction , 2012, NAACL.

[4]  Marcin Junczys-Dowmunt,et al.  Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task , 2018, NAACL.

[5]  Sunita Sarawagi,et al.  Parallel Iterative Edit Models for Local Sequence Transduction , 2019, EMNLP.

[6]  Shamil Chollampatt,et al.  Neural Quality Estimation of Grammatical Error Correction , 2018, EMNLP.

[7]  Yuji Matsumoto,et al.  Mining Revision Log of Language Learning SNS for Automated Japanese Error Correction of Second Language Learners , 2011, IJCNLP.

[8]  Ting Liu,et al.  Attention-over-Attention Neural Networks for Reading Comprehension , 2016, ACL.

[9]  Quoc V. Le,et al.  ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators , 2020, ICLR.

[10]  Ted Briscoe,et al.  Automatic Extraction of Learner Errors in ESL Sentences Using Linguistically Enhanced Alignments , 2016, COLING.

[11]  Artem Chernodub,et al.  GECToR – Grammatical Error Correction: Tag, Not Rewrite , 2020, BEA.

[12]  Lysandre Debut,et al.  HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.

[13]  Ted Briscoe,et al.  Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction , 2017, ACL.

[14]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[15]  Kentaro Inui,et al.  An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction , 2019, EMNLP.

[16]  Huanbo Luan,et al.  Improving Back-Translation with Uncertainty-based Confidence Estimation , 2019, EMNLP.

[17]  Ming Zhou,et al.  Fluency Boost Learning and Inference for Neural Grammatical Error Correction , 2018, ACL.

[18]  Mamoru Komachi,et al.  Multi-Head Multi-Layer Attention to Deep Language Representations for Grammatical Error Detection , 2019, Computación y Sistemas.

[19]  Kentaro Inui,et al.  Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction , 2020, ACL.

[20]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[21]  H. Ng,et al.  A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction , 2018, AAAI.

[22]  Marek Rei,et al.  Semi-supervised Multitask Learning for Sequence Labeling , 2017, ACL.

[23]  Joel R. Tetreault,et al.  JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction , 2017, EACL.

[24]  Masato Hagiwara,et al.  GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors , 2019, LREC.

[25]  Ted Briscoe,et al.  Grammatical error correction using neural machine translation , 2016, NAACL.

[26]  Helen Yannakoudakis,et al.  Neural Sequence-Labelling Models for Grammatical Error Correction , 2017, EMNLP.

[27]  Wei Zhao,et al.  Denoising based Sequence-to-Sequence Pre-training for Text Generation , 2019, EMNLP.

[28]  Marc'Aurelio Ranzato,et al.  Analyzing Uncertainty in Neural Machine Translation , 2018, ICML.

[29]  Shamil Chollampatt,et al.  Cross-Sentence Grammatical Error Correction , 2019, ACL.

[30]  Shamil Chollampatt,et al.  Exploiting N-Best Hypotheses to Improve an SMT Approach to Grammatical Error Correction , 2016, IJCAI.

[31]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[32]  Daniel Jurafsky,et al.  Noising and Denoising Natural Language: Diverse Backtranslation for Grammar Correction , 2018, NAACL.

[33]  Noam M. Shazeer,et al.  Corpora Generation for Grammatical Error Correction , 2019, NAACL.

[34]  W. Bruce Croft,et al.  Linear feature-based models for information retrieval , 2007, Information Retrieval.

[35]  Hwee Tou Ng,et al.  Building a Large Annotated Corpus of Learner English: The NUS Corpus of Learner English , 2013, BEA@NAACL-HLT.

[36]  Matt Post,et al.  Ground Truth for Grammatical Error Correction Metrics , 2015, ACL.

[37]  Lucia Specia,et al.  Multi-Hypothesis Machine Translation Evaluation , 2020, ACL.

[38]  Aliaksei Severyn,et al.  Encode, Tag, Realize: High-Precision Text Editing , 2019, EMNLP.

[39]  Wei Zhao,et al.  Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data , 2019, NAACL.

[40]  Helen Yannakoudakis,et al.  A New Dataset and Method for Automatically Grading ESOL Texts , 2011, ACL.

[41]  Anders Søgaard,et al.  Jointly Learning to Label Sentences and Tokens , 2018, AAAI.

[42]  Mamoru Komachi,et al.  TMU Transformer System Using BERT for Re-ranking at BEA 2019 Grammatical Error Correction on Restricted Track , 2019, BEA@ACL.

[43]  Ted Briscoe,et al.  The BEA-2019 Shared Task on Grammatical Error Correction , 2019, BEA@ACL.

[44]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.