Abstract
Our research aims to provide writers with automated tools to detect grammatical usage errors and thus improve their writing. Correct English usage is often lacking in scientific and industry papers. [16] has compiled 130 common English usage errors. We address the automated detection of these errors, and their variations, that writers often make. Grammar checkers, e.g., [9] and [11], also implement error detection. Other researchers have employed machine learning and neural networks to detect errors. We parse only the part of speech (POS) tags using different levels of generality of POS syntax and word-sense semantics. Our results provide accurate error detection and are feasible for a wide range of errors. Our algorithm specifies precisely the ability to increase or decrease the generality in order to prevent a large number of false positives. We derive this observation as a result of using The Brown corpus, which consists of 55, 889 untagged sentences, covering most genres of English usage, both fiction and non-fiction. This corpus was much larger than any corpus employed by related researchers. We implemented 80 of Swan’s most common 130 rules; and detected 35 true positives distributed among 15 of Swan’s rules. Such a low true positive rate, 35/55889, had been expected. No false positives were detected. We employed a separate, smaller, test suite of both true positive and true negative examples. Our system, as expected, correctly detected errors in all the true positive examples, and ignored all the true negative ones. The Language-Tool system had a detection rate of 28/130 = 22%; Grammarly had a detection rate of 60/130 = 46%. Our results show significant improvement in the detection of common English usage errors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Rated first out of 20 grammar checking applications.
- 2.
Rated fifth out of 20 grammar checking applications.
- 3.
The target foreign language is the language one is translating into, e.g., from Dutch into English.
- 4.
Fluency, in machine translation, means how natural the resultant translation is to a native speaker of the language.
References
Al-Shujairi, Y., Tan, H.: Grammar errors in the writing of Iraqi English language learners (2017). http://journals.aiac.org.au/index.php/IJELS/article/view/3925. Accessed 9–10 2018
BrownCorpus: Brown Corpus (2018). https://www1.essex.ac.uk/linguistics/external/clmt/w3c/corpus_ling/content/corpora/list/private/brown/brown.html. Accessed 9–10 2018
De-Felice, R.: Automatic error detection in non-native English. Oxford University, Ph.D. thesis (2008)
Feng, H., Saricaoglu, A., Chukharev-Hudilainen, E.: Automated error detection for developing grammar proficiency of ESl learners. Calico J.: Comput. Assist. Lang. Instr. Consortium 33, 49 (2016)
Fernando, S., Dias, A.: Mastering language use and usage: repositions perceived according to cognitive linguistics (2017). http://www.serie-estudos.ucdb.br/index.php/serie-estudos/article/view/1087. Accessed 9–10 2018
Foster, J., Andersen, Ø.E.: GenERRate: generating errors for use in grammatical error detection. In: 2009 Proceedings of the Fourth Workshop on Innovative use of NLP for Building Educational Applications, EdAppsNLP (2009)
Garimella, M.: Detecting article errors in English learner essays with recurrent neural networks. Department of Computational Linguistics (M.A.), Brandeis University (2016)
Garnier, M.: Correcting erroneous N+N structures in the productions of French users of English. Nottingham University (2011)
Grammarly: Grammarly (2019). https://app.grammarly.com. Accessed 1 2019
Hope, T., Resheff, Y., Lieder, I.: Learning Tensor Flow. O’Reilly, Beijing (2017)
LanguageTool: Language-Tool (2018). https://languagetool.org/. Accessed 9–10 2018
Leacock, C., Chodorow, M., Gamon, M., Tetreault, J.: Automated Grammatical Error Detection for Language Learners, 2nd edn. Morgan and Claypool Publishers, San Rafael (2014)
NeurographStudio: Neurograph Studio (2018). http://neuroph.sourceforge.net/download.html/. Accessed 5–6 2018
Skukla, N.: Machine Learning with Tensor Flow. Manning Publications, New York (2018)
StandfordNLPGroup: Standford NLP Group (2018). http://nlp.stanford.edu/projects/stat-parsing.shtml. Accessed 6–7 2017
Swan, M.: Practical English Usage, 3rd edn. Oxford University Press, Oxford (2015)
Tetreault, J., Chodorow, M.: The ups and downs of preposition error detection in ESL writing. In: Proceedings of the 22nd International Conference on Computational Linguistics 1, COLING 2008 (2008)
Tezcan, A., Hoste, V., Macken, L.: A neural network architecture for detecting grammatical errors in statistical machine translation. Prague Bull. Math. Linguis. 108, 133–145 (2017)
Xue, H.: Computational models of problems with writing of English as a second language learners. Ph.D. thesis, Pittsburgh University (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendices
Appendix
A Swan Error 326_1.
B Our Own Related Neural Network
Lets first review the mechanics of our off-the-shelf neural network, [13], that we employed.
First, the network’s input and output nodes are chosen with values—these are concrete examples with and without errors. Second, the network is trained using these examples. Finally, the network is tested with similar (but not identical) examples. If the network does not converge during training, use a different architecture—hidden nodes, but retain with the original training examples.
Swan’s errors (634 of them) can be listed in any numerical order, and our subset (at the time) of 52 errors was mapped into binary digits. 000000—0—constitutes no error in the input string. Six binary digits were enough to cover 52 errors—11110 would be Swan’s error #30. Text strings were converted, internally, into decimal numbers; padding to the right occurred to make the sentences of equal length. These converted text strings constitute our training input. Our final training input and output is in Table 1. The last error example, 463.2 (Swan), involves the weather—the simple present tense should not be used for talking about a temporary condition.
The training algorithm [13] was back-propagation; we chose a slow training rate to minimize errors–0.01. While training, the network failed to converge. Because of this failure, we tried separate digits for each error (using significantly more nodes)—to no avail. Hidden layers were varied from three to eight layers; the number of nodes per layer varied from nine to 100. In other words, many combinations were tried—none of the architectures converged for our given (training) inputs and outputs. Convergence would decrease and then stop, and stay constant. Thus, no testing could be performed on the neural network.
However, testing the error detection for exactly two rules, and a non-error state did work as expected. We are not surprised—neural networks require many examples and counter examples—but each Swan rule usually has on average five examples, and at most ten examples which is not nearly enough for training purposes.
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Immes, L., Levkowitz, H. (2019). Detection of Common English Grammar Usage Errors. In: Kozielski, S., Mrozek, D., Kasprowski, P., Małysiak-Mrozek, B., Kostrzewa, D. (eds) Beyond Databases, Architectures and Structures. Paving the Road to Smart Data Processing and Analysis. BDAS 2019. Communications in Computer and Information Science, vol 1018. Springer, Cham. https://doi.org/10.1007/978-3-030-19093-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-19093-4_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19092-7
Online ISBN: 978-3-030-19093-4
eBook Packages: Computer ScienceComputer Science (R0)