Learning Persian grammar with the aid of an intelligent feedback generator

Mirzaeian, Vahid Reza; Kohzadi, Hamedreza; Azizmohammadi, Fatemeh

doi:10.1016/j.engappai.2015.09.012

Cited by 6 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For slightly more than a half (56%) of the studies, no implementation information is specified by the authors, including languages, platform or software. The most commonly used languages are JavaScript (Karavirta et al, 2012), Java (Mirzaeian et al, 2016;Di Eugenio et al, 2008), C++ or C# languages (Kelly et al, 2008;Akçapınar, 2015), and Python (Roselli et al, 2008). The systems that work with gesture or movements data tend to use Microsoft Kinect (Nguyen et al, 2012;Barmaki and Hughes, 2015).…”

Section: Methodsmentioning

confidence: 99%

“…The distribution of feedback adaptiveness levels is shown in Figure 10 (left). 50.5% of the studies employed task adaptiveness (Kazi et al, 2010;Nguyen et al, 2012;Mirzaeian et al, 2016). In comparison, only 15.6% of the systems reported to have student adaptiveness (Schaffer et al, 2017;Roselli et al, 2008;Chung et al, 2013).…”

Section: Methodsmentioning

confidence: 99%

“…The distribution of the student group sizes used for evaluation is discussed below. Out of the papers that reported evaluation, only 3 of them (3%) did not use any student group for evaluation (Mirzaeian et al, 2016). Similarly, only a small proportion of studies (5%) applied their tool to a massive (over 400) group of students.…”

Section: Group Sizementioning

confidence: 99%

See 2 more Smart Citations

A review of automated feedback systems for learners: Classification framework, challenges and opportunities

Deeva

Bogdanova

Serral

et al. 2021

Computers & Education

133

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A review of automated feedback systems for learners: Classification framework, challenges and opportunities

Deeva

Bogdanova

Serral

et al. 2021

Computers & Education

133

View full text Add to dashboard Cite

“…Natural language processing (NLP) relies on the design of powerful and intelligent algorithms that can automatically process and understand complex patterns within the text [1][2][3]. Automatic NLP systems that can detect and correct grammar and word usage errors require a large amount of correct and incorrect labeled data.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Grammatical Error Generation: Application to Persian Language

Golizadeh¹,

Golizadeh²,

Forouzanfar³

2022

IJNLC

View full text Add to dashboard Cite

Grammatical error correction (GEC) greatly benefits from large quantities of high-quality training data. However, the preparation of a large amount of labelled training data is time-consuming and prone to human errors. These issues have become major obstacles in training GEC systems. Recently, the performance of English GEC systems has drastically been enhanced by the application of deep neural networks that generate a large amount of synthetic data from limited samples. While GEC has extensively been studied in languages such as English and Chinese, no attempts have been made to generate synthetic data for improving Persian GEC systems. Given the substantial grammatical and semantic differences of the Persian language, in this paper, we propose a new deep learning framework to create large enough synthetic sentences that are grammatically incorrect for training Persian GEC systems. A modified version of sequence generative adversarial net with policy gradient is developed, in which the size of the model is scaled down and the hyperparameters are tuned. The generator is trained in an adversarial framework on a limited dataset of 8000 samples. Our proposed adversarial framework achieved bilingual evaluation understudy (BLEU) scores of 64.5% on BLEU-2, 44.2% on BLEU-3, and 21.4% on BLEU-4, and outperformed the conventional supervised-trained long short-term memory using maximum likelihood estimation and recently proposed sequence labeler using neural machine translation augmentation. This shows promise toward improving the performance of GEC systems by generating a large amount of training data.

show abstract