Writing Style Assistance

Overview

Grammar-correcting software provides corrections, suggestions, and tips in much the same manner as a spellchecker. Each of these programs offers plagiarism-detection and “proofreading,” and all offer training games to improve a user’s knowledge of English grammar and its rules. According to each product’s own website, all use artificial intelligence and are developed by experts in linguistics. Much like spellcheckers, these tools are most useful for proficient and skilled writers to search for typographical errors; for writers who are acquiring English, or who have a specific language or learning disability, and who have more frequent or more complex errors, these programs are less successful and less easy to use. This is contrary to some of the advertisements and claims on most product websites; however, Editor offers further guidance for users who are English Language Learners.

Ginger offers word-prediction, a built-in thesaurus, a sentence-rephraser, and a text-to-speech feature for reading a composition back to the author. PaperRater offers a vocabulary-building game, as well as grammar and spelling scans; its primary emphasis is on predicting a grade for a particular assignment, and giving the user a personal writing score against peers of the same age and education level based on vocabulary, accuracy, originality and sentence length. Grammarly and WhiteSmoke both operate automatically once activated, across all word-processing and browsers. Both include a “style checker” which operates primarily by providing vocabulary suggestions. WhiteSmoke includes a range of translation services. All four have received positive reviews from users, but none has received much experimental analysis. It is worth noting that none of these four programs was able to successfully correct, or consistently identify, complex errors, and none was able to correct all simple errors (subject-verb agreement, run-on sentences, verb tenses, word choice) in sentences that were sufficiently complex or long.

Several other grammar-checkers exist, and most are very similar to these. A number of other websites advertising alternate grammar checkers offer identical products under different names.

Research Rating: The efficacy of these products has not been demonstrated by empirical study.

Special Consideration: Workflow

Exact prices change frequently, which is why only approximate ranges are listed.

$ - Under $5

$$ - Between $6 and $50

$$$ - Between $51 and $250

$$$$ - Over $250

References

Dale, R. (2016). Checking in on grammar checking. Natural Language Engineering, 22(3), 491-495. doi:10.1017/S1351324916000061

Dale, R. (2017). The commercial NLP landscape in 2017. Natural Language Engineering, 23(4), 641-647. doi:10.1017/S1351324917000237

Dale, R. (2008). Industry Watch: Language technology, meet social networking. Natural Language Engineering, 14(2), 283-288. doi:10.1017/S1351324908004683

Hallur, Akshay. “Grammarly vs. WhiteSmoke vs. Ginger – The Shootout Comparison!” Accessed October, 2017.

Leacock, C., Chodorow, M., Gamon, M.,and Tetreault, J. (2010.) Automated Grammatical Error Detection for Language Learners. Morgan & Claypool Publishers.

Napoles, C., Sakaguchi, K., and Tetreault, J. (2016) There’s No Comparison: Reference-less Evaluation Metrics in Grammatical Error Correction

Ng, H. T., Wu, S. M., Briscoe, T., Hadiwinoto, C., Hendy Susanto, R., and Bryant, C. 2014. The CoNLL-2014 Shared Task on Grammatical Error Correction. Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task, 1–14.

Thiesmeyer, E. and Thiesmeyer, J. “Comparing Grammar Checkers: Holding Grammar Scammers' Feats to the Fire.” (2014) Accessed November, 2017.

Thiesmeyer, E. and Thiesmeyer, J. “About Editor Software.” Accessed November, 2017.