Neural Network Translation Models for Grammatical Error Correction

2 code implementations • 1 Jun 2016 • Shamil Chollampatt, Kaveh Taghipour, Hwee Tou Ng

Phrase-based statistical machine translation (SMT) systems have previously been used for the task of grammatical error correction (GEC) to achieve state-of-the-art accuracy.

Grammatical Error Correction Machine Translation +2

Exploiting N-Best Hypotheses to Improve an SMT Approach to Grammatical Error Correction

no code implementations • 1 Jun 2016 • Duc Tam Hoang, Shamil Chollampatt, Hwee Tou Ng

Grammatical error correction (GEC) is the task of detecting and correcting grammatical errors in texts written by second language learners.

Grammatical Error Correction Machine Translation +1

Adapting Grammatical Error Correction Based on the Native Language of Writers with Neural Network Joint Models

no code implementations • EMNLP 2016 • Shamil Chollampatt, Duc Tam Hoang, Hwee Tou Ng

Grammatical Error Correction Machine Translation

Connecting the Dots: Towards Human-Level Grammatical Error Correction

no code implementations • WS 2017 • Shamil Chollampatt, Hwee Tou Ng

We build a grammatical error correction (GEC) system primarily based on the state-of-the-art statistical machine translation (SMT) approach, using task-specific features and tuning, and further enhance it with the modeling power of neural network joint models.

Grammatical Error Correction Language Modelling +2

A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction

3 code implementations • 26 Jan 2018 • Shamil Chollampatt, Hwee Tou Ng

We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network.

Grammatical Error Correction Language Modelling +1

A Reassessment of Reference-Based Grammatical Error Correction Metrics

1 code implementation • COLING 2018 • Shamil Chollampatt, Hwee Tou Ng

Previous studies of the correlation of these metrics with human quality judgments were inconclusive, due to the lack of appropriate significance tests, discrepancies in the methods, and choice of datasets used.

Grammatical Error Correction Machine Translation +1

Neural Quality Estimation of Grammatical Error Correction

1 code implementation • EMNLP 2018 • Shamil Chollampatt, Hwee Tou Ng

We also show that a state-of-the-art GEC system can be improved when quality scores are used as features for re-ranking the N-best candidates.

Grammatical Error Correction Machine Translation +1

Cross-Sentence Grammatical Error Correction

1 code implementation • ACL 2019 • Shamil Chollampatt, Weiqi Wang, Hwee Tou Ng

Automatic grammatical error correction (GEC) research has made remarkable progress in the past decade.

Grammatical Error Correction Sentence

Lexically Constrained Neural Machine Translation with Levenshtein Transformer

1 code implementation • ACL 2020 • Raymond Hendy Susanto, Shamil Chollampatt, Liling Tan

This paper proposes a simple and effective algorithm for incorporating lexical constraints in neural machine translation.

Machine Translation Translation

Can Automatic Post-Editing Improve NMT?

1 code implementation • EMNLP 2020 • Shamil Chollampatt, Raymond Hendy Susanto, Liling Tan, Ewa Szymanska

To ascertain our hypothesis, we compile a larger corpus of human post-edits of English to German NMT.

Automatic Post-Editing NMT +2