This paper describes an English grammatical error correction system for CoNLL2013 shared task. Error types covered by our system are article/determiner, preposition, and noun number agreement. This work is our first attempt on grammatical error correction research. In this work, we only focus on reimplementing the techniques presented before and optimizing the performance. As a result of the im...

Automatic grammatical error detection for Chinese has been a big challenge for NLP researchers for a long time, mostly due to the flexible and irregular ways in the expressing of this language. Strictly speaking, there is no evidence of a series of formal and strict grammar rules for Chinese, especially for the spoken Chinese, making it hard for foreigners to master this language. The CFL share...

Grammatical error correction (GEC) is the task of automatically correcting grammatical errors in written text. Previous research has mainly focussed on individual error types and current commercial proofreading tools only target limited error types. As sentences produced by learners may contain multiple errors of different types, a practical error correction system should be able to detect and ...

Different approaches to high-quality grammatical error correction have been proposed recently, many of which have their own strengths and weaknesses. Most of these approaches are based on classification or statistical machine translation (SMT). In this paper, we propose to combine the output from a classification-based system and an SMT-based system to improve the correction quality. We adopt t...

This paper presents the first study using neural machine translation (NMT) for grammatical error correction (GEC). We propose a twostep approach to handle the rare word problem in NMT, which has been proved to be useful and effective for the GEC task. Our best NMTbased system trained on the CLC outperforms our SMT-based system when testing on the publicly available FCE test set. The same system...

We propose a joint inference algorithm for grammatical error correction. Different from most previous work where different error types are corrected independently, our proposed inference process considers all possible errors in a uni ed framework. We use integer linear programming (ILP) to model the inference process, which can easily incorporate both the power of existing error classi ers and ...

This paper explores the generation of artificial errors for correcting grammatical mistakes made by learners of English as a second language. Artificial errors are injected into a set of error-free sentences in a probabilistic manner using statistics from a corpus. Unlike previous approaches, we use linguistic information to derive error generation probabilities and build corpora to correct sev...

This paper presents a rule-based approach for correcting grammatical errors made by non-native speakers of English. The approach relies on the differences in the outputs of two POS taggers. This paper is submitted in response to CoNLL-2014 Shared Task.

A fast growing area in Natural Language Processing is the use of automated tools for identifying and correcting grammatical errors made by language learners. This growth, in part, has been fueled by the needs of a large number of people in the world who are learning and using a second or foreign language. For example, it is estimated that there are currently over one billion people who are non-...

We propose a neural encoder-decoder model with reinforcement learning (NRL) for grammatical error correction (GEC). Unlike conventional maximum likelihood estimation (MLE), the model directly optimizes towards an objective that considers a sentence-level, task-specific evaluation metric, avoiding the exposure bias issue in MLE. We demonstrate that NRL outperforms MLE both in human and automated...