Browse > Natural Language Processing > Grammatical Error Correction

Grammatical Error Correction

28 papers with code · Natural Language Processing

Throughout, the peer teach and I found the lesson successful as my peer present to be my students are clearly understand on the given topic. I introduce the lesson with a short game which is Chinese Whisper my peers are well participated in the game. The game is engaging as I know from the feedback from my peers that is very engaging for them and they did enjoying it. The major task for the learning went to my expectations, students completed the given task smoothly. In addition the grouping students to carried out students is the most effective approach where student have a chance to interact with their peers to share their understanding to each other.

However, within the learning process there are some of the part that students are confusing. In this case there were a lot of noise and could disturbing the others because I thought they can understand everything and they are mature enough to find the meaning. My peer recommend that it is important to introduce the new vocabulary to student even they are not really a student. They also propose that what you did your peer teaching it will helpful for me to teach students so I have make sure to do to carried out what I’ve got to make me not forget when I’m out to schools. According to Vygotsky idea on Zone of Proximal Development (ZPD), is a distance between students’ actual developmental level and potential level with direct instruction or peer collaboration. This theory suggests that the experiences of students’ with words grow, it becomes easier to learn new words.

Therefore, regarding to my feedback from my peers they stated that I have to be serious in my delivery, they also mention that giving a positive feedback to students’ is very important to feel the belonging of the learning. For me, I found this feedback more meaningful and helpful in terms of construction the effective lesson to stimulate students’ readiness to learn.

Leaderboards

Greatest papers with code

Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction

ACL 2017 chrisjbryant/errant

Until now, error type performance for Grammatical Error Correction (GEC) systems could only be measured in terms of recall because system output is not annotated.

GRAMMATICAL ERROR CORRECTION

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

26 Jan 2018nusnlp/mlconvgec2018

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

Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data

NAACL 2019 2019 zhawe01/fairseq-gec

It is the first time copying words from the source context and fully pre-training a sequence to sequence model are experimented on the GEC task.

DENOISING GRAMMATICAL ERROR CORRECTION MACHINE TRANSLATION MULTI-TASK LEARNING

JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction

EACL 2017 keisks/jfleg

We present a new parallel corpus, JHU FLuency-Extended GUG corpus (JFLEG) for developing and evaluating grammatical error correction (GEC).

GRAMMATICAL ERROR CORRECTION

Parallel Iterative Edit Models for Local Sequence Transduction

IJCNLP 2019 awasthiabhijeet/PIE

We present a Parallel Iterative Edit (PIE) model for the problem of local sequence transduction arising in tasks like Grammatical error correction (GEC).

GRAMMATICAL ERROR CORRECTION OPTICAL CHARACTER RECOGNITION

Neural Quality Estimation of Grammatical Error Correction

EMNLP 2018 nusnlp/neuqe

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

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

3 Jul 2018getao/human-performance-gec

Neural sequence-to-sequence (seq2seq) approaches have proven to be successful in grammatical error correction (GEC).

GRAMMATICAL ERROR CORRECTION