We present a novel beam-search decoder for grammatical error correction. The decoder iteratively generates new hypothesis corrections from current hypotheses and scores them based on features of grammatical correctness and fluency. These features include scores from discriminative classifiers for specific error categories, such as articles and prepositions. Unlike all previous approaches, our m...

This paper identifies and examines the key principles underlying building a state-of-theart grammatical error correction system. We do this by analyzing the Illinois system that placed first among seventeen teams in the recent CoNLL-2013 shared task on grammatical error correction. The system focuses on five different types of errors common among non-native English writers. We describe four des...

The availability of learner corpora, especially those which have been manually error-tagged or shallow-parsed, is still limited. This means that researchers do not have a common development and test set for natural language processing of learner English such as for grammatical error detection. Given this background, we created a novel learner corpus that was manually error-tagged and shallowpar...

A linear code C is called a group code if C is an ideal in a group algebra K[G] where K is a ring and G is a finite group. Many classical linear error-correcting codes can be realized as ideals of group algebras. Berman [1], in the case of characteristic 2, and Charpin [2], for characteristic p = 2, proved that all generalized Reed–Muller codes coincide with powers of the radical of the group a...

The sequential structure and variable length of speech data suggests the use of structural techniques such as Hidden Markov Models or Grammatical Inference systems. In contrast, geometric and classical (non-recurrent) connectionist methods deal with objects represented in a vector space. This means that some method has to be used to transform variable-length strings of parameters into d-dimensi...

This paper reports how to build a Chinese Grammatical Error Diagnosis system based on the conditional random fields (CRF). The system can find four types of grammatical errors in learners’ essays. The four types or errors are redundant words, missing words, bad word selection, and disorder words. Our system presents the best false positive rate in 2015 NLP-TEA-2 CGED shared task, and also the b...

This is a report on the methods used and results obtained by the UW-Stanford team for the Automated Evaluation of Scientific Writing (AESW) Shared Task 2016 on grammatical error detection. This team developed a symbolic grammar-based system augmented with manually defined mal-rules to accommodate and identify instances of highfrequency grammatical errors. System results were entered both for th...

We apply machine learning techniques to classify automatically a set of verbs into lexical semantic classes, based on distributional approximations of diathe-ses, extracted from a very large annotated corpus. Distributions of four grammatical features are sufficient to reduce error rate by 50% over chance. We conclude that corpus data is a usable repository of verb class information, and that c...

This study set out to investigate the effect of peer- editing as a metacognitive strategy on the development of writing. It was hypothesized that peer-editing could be used to raise grammatical and compositional awareness of the learners. Forty pre-intermediate sophomores at Islamic Azad University-Tabriz Branch participated in the study, taking the course Writing I. To warrant the initial homo...

We apply machine learning techniques to classify automatically a set of verbs into lexical semantic classes, based on distributional approximations of diathe-ses, extracted from a very large annotated corpus. Distributions of four grammatical features are suucient to reduce error rate by 50% over chance. We conclude that corpus data is a usable repository of verb class information, and that cor...