---
title: "A Benchmark Corpus of English Misspellings and a"
description: "The authors release TOEFL-Spell, built from 883 medium- and… 88.12% accuracy on TOEFL-Spell. 46 references, cited by 14 papers here."
authors: ["Michael Flor", "Michael Fried", "Alla Rozovskaya"]
year: 2019
venue: "Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications"
source: "https://aclanthology.org/W19-4407/"
doi: "10.18653/v1/w19-4407"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/flor-2019-benchmark-corpus-english-misspellings-minimally/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/flor-2019-benchmark-corpus-english-misspellings-minimally/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2019](https://md.research.elamur.ai/free/en/papers/2019/page/6/) / A Benchmark Corpus of English Misspellings and a Minimally-supervised Model for Spelling Correction

# A Benchmark Corpus of English Misspellings and a Minimally-supervised Model for Spelling Correction

**Authors:** [Michael Flor](https://md.research.elamur.ai/free/en/authors/michael-flor/), Michael Fried and [Alla Rozovskaya](https://md.research.elamur.ai/free/en/authors/alla-rozovskaya/) · **Year:** 2019 · **Venue:** [Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications](https://md.research.elamur.ai/free/en/venues/bea/) ([BEA 2019](https://md.research.elamur.ai/free/en/venues/bea/2019/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/W19-4407/) · [PDF](https://aclanthology.org/W19-4407.pdf) · [DOI 10.18653/v1/w19-4407](https://doi.org/10.18653/v1/w19-4407) · [OpenAlex](https://openalex.org/W2971091580)

**Citations:** 25 citations (OpenAlex, 2026-10-14) · [14](https://md.research.elamur.ai/free/en/papers/flor-2019-benchmark-corpus-english-misspellings-minimally/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Non-word spelling correction has a long research history, but systems have mostly been tested on synthetic typos or closed datasets, so results are hard to compare. Learner writing is especially difficult: non-native authors misspell more often, make more multi-character edits, and their errors often sit next to other non-standard usage. The authors release TOEFL-Spell, built from 883 medium- and high-scored essays in the public TOEFL11 collection. Two trained annotators started from dictionary-lookup highlights, then searched for anything the lookup missed, recording every non-word misspelling with its correction. The authors also build a ranker for candidate corrections that needs little labelled data. It combines word-internal signals (orthographic and phonetic similarity, frequency) with context signals (n-gram counts, word2vec embeddings, and whether the candidate appears elsewhere in the same essay). The ranker reaches 88.12% accuracy on TOEFL-Spell. Moved unchanged to clinical notes, it roughly matches a system built and tuned for that domain. The work gives the field a shared benchmark and a cheap, portable baseline.

## Key points
- TOEFL-Spell covers 296,141 words with 6,121 non-word errors (a 2.07% word error rate), 3,958 distinct misspellings and about 1.015 corrections per misspelling. 82.76% of errors are one edit away from the target and 12.56% are two edits away.
- The best model ranks the gold correction first in about 88% of cases and within the top five in 96.7%. Training on very little annotated data costs under 1 point.
- Context features cut errors by about 45%, adding roughly 10 accuracy points on TOEFL-Spell and 7 on clinical notes.
- In ablations, orthographic similarity matters most: removing it on clinical data costs almost 30 points. Frequency and the same-document features help least.
- On the clinical corpus of Fivez et al. (2017a), the model is comparable when off-the-shelf dictionaries are used. With a "completed lexicon", the Fivez system wins 93.02 vs 89.35 (Perceptron). The gap comes from very rare added medical terms, on which the context features never fire.

## Interesting ideas
- Rank candidates with a small learned model over a handful of interpretable signals (string distance, sound distance, local n-grams, embeddings), so each feature's contribution can be measured by ablation.
- Treat a candidate's appearance elsewhere in the same document as evidence, since writers tend to reuse their own words.
- Classify wrong top answers by their relation to the gold: inflectional variant, derivational relative, or regional/close spelling variant. This separates near-misses from real failures.
- Distinguish off-the-shelf evaluation from evaluation where test vocabulary was added to the lexicon, because the latter leaks information and inflates scores.
- Make annotation exhaustive by having humans confirm machine highlights and then hunt for errors the tool missed.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (tokens): A pre-tagging normalizer could propose corrections for out-of-dictionary tokens and log which feature tipped the choice, keeping the repair explainable before lemma lookup.
- **I2** (world): When an unknown string closely resembles an entity already present in the text's world, that existing entity could be preferred as the referent, with the link recorded as a justification.
- **I3** (learn): Evaluation reports could bucket mismatches the same way, so lemma-level agreement is not counted as a full error.
- **I4** (learn): Benchmarks could include a no-leak condition as a negative control, checking that gains do not come from lexicon entries derived from the test set.
- **I5** (learn): Silver data produced by witness parsers could be reviewed the same way, with reviewers also looking for problems that none of the parsers flagged.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (3): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,263 works · [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,220 works · [🖍️ Grammatical error correction & learner language](https://md.research.elamur.ai/free/en/topics/grammatical-error-correction/) · 156 works

## Cite

Cite as: Michael Flor, Michael Fried and Alla Rozovskaya. 2019. A Benchmark Corpus of English Misspellings and a Minimally-supervised Model for Spelling Correction. Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{flor2019benchmark,
  title = {{A Benchmark Corpus of English Misspellings and a Minimally-supervised Model for Spelling Correction}},
  author = {Michael Flor, Michael Fried and Alla Rozovskaya},
  booktitle = {Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications},
  year = {2019},
  doi = {10.18653/v1/w19-4407},
  url = {https://doi.org/10.18653/v1/w19-4407}
}
```

- [← previous WikiCREM: A Large Unsupervised Corpus for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/kocijan-2019-wikicrem-large-unsupervised-corpus-coreference/)
- [next → A Simple Joint Model for Improved Contextual Neural Lemmatization](https://md.research.elamur.ai/free/en/papers/malaviya-2019-simple-joint-model-improved-contextual/)
- [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/page/6/)

## References

46 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Daniel Dahlmeier, Hwee Tou Ng, and Siew Mei Wu. 2013. [Building a large annotated corpus of learner English: The NUS Corpus of Learner English](https://md.research.elamur.ai/free/en/papers/dahlmeier-2013-building-large-annotated-corpus-learner/). In Proceedings of the Eighth Workshop on Innovative Use of NLP for Building Educational Applications, pages 22–31, Atlanta, Georgia. Association for Computational Linguistics.
2. Jon L. Bentley and Robert Sedgewick. 1997. Fast algorithms for sorting and searching strings. In Proceedings of the 8th Annual ACM-SIAM Symposium on Discrete Algorithms, SODA97, pages 360–399. ACM. [↗](https://doi.org/10.5555/314161.314321)
3. Daniel Blanchard, Joel Tetreault, Derrick Higgins, Aoife Cahill, and Martin Chodorow. 2013. TOEFL11: A Corpus of Non-Native English. Research Report ETS RR13-24. Educational Testing Service, Princeton, NJ, USA. [↗](https://doi.org/10.1002/j.2333-8504.2013.tb02331.x)
4. Frederick Damerau. 1964. A technique for computer detection and correction of spelling errors. Communications of the ACM, 7(3):659–664. [↗](https://doi.org/10.1145/363958.363994)
5. Semire Dikli. 2006. An overview of automated scoring of essays. Journal of Technology, Learning, and Assessment, 5:4–35. [find](https://scholar.google.com/scholar?q=Semire+Dikli%2E+2006%2E+An+overview+of+automated+scoring+of+essays%2E+Journal+of+Technology%2C+Learning%2C+and+Assessment%2C+5%3A4%E2%80%9335%2E)
6. Daniel Blanchard, Joel Tetreault, Derrick Higgins, Aoife Cahill, and Martin Chodorow. 2014. ETS Corpus of Non-Native Written English, Catalog No. LDC2014T06. Linguistic Data Consortium, Philadelphia, PA, USA. [find](https://scholar.google.com/scholar?q=Daniel+Blanchard%2C+Joel+Tetreault%2C+Derrick+Higgins%2C+Aoife+Cahill%2C+and+Martin+Chodorow%2E+2014%2E+ETS+Corpus+of+Non%2DNative+Written+English%2C+Catalog+No%2E+LDC2014T06%2E+Linguistic+Data+Consortium%2C+Philadelphia%2C+)
7. Pieter Fivez, Simon Suster, and Walter Daelemans. 2017a. Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings. In BioNLP 2017, pages 143–148, Vancouver, Canada,. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Pieter+Fivez%2C+Simon+Suster%2C+and+Walter+Daelemans%2E+2017a%2E+Unsupervised+Context%2DSensitive+Spelling+Correction+of+Clinical+Free%2DText+with+Word+and+Character+N%2DGram+Embeddings%2E+In+BioNLP+2017%2C+pages+143%E2%80%931)
8. Gerlof Bouma. 2009. Normalized (pointwise) mutual information in collocation extraction. In From Form to Meaning: Processing Texts Automatically, Proceedings of the Biennial GSCL Conference, pages 31–40, Tbingen. Gunter Narr Verlag. [find](https://scholar.google.com/scholar?q=Gerlof+Bouma%2E+2009%2E+Normalized+%28pointwise%29+mutual+information+in+collocation+extraction%2E+In+From+Form+to+Meaning%3A+Processing+Texts+Automatically%2C+Proceedings+of+the+Biennial+GSCL+Conference%2C+pages+31%E2%80%93)
9. Pieter Fivez, Simon Łuster, and Walter Daelemans. 2017b. Unsupervised Context-Sensitive Spelling Correction of English and Dutch Clinical Free-Text with Word and Character N-Gram Embeddings. In Arxiv. [↗](https://doi.org/10.48550/arxiv.1710.07045)
10. Thorsten Brants and Alex Franz. 2006. Web 1T 5-gram Version 1. Linguistic Data Consortium. [↗](https://doi.org/10.35111/cqpa-a498)
11. Eric Brill and Robert C. Moore. 2000. [An improved error model for noisy channel spelling correction](https://md.research.elamur.ai/free/en/papers/brill-2000-improved-error-model-noisy-channel/). In Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics, pages 286– 293.
12. Michael Flor. 2012. Four types of context for automatic spelling correction. Traitement Automatique des Langues (TAL), 53(3):61–99. [find](https://scholar.google.com/scholar?q=Michael+Flor%2E+2012%2E+Four+types+of+context+for+automatic+spelling+correction%2E+Traitement+Automatique+des+Langues+%28TAL%29%2C+53%283%29%3A61%E2%80%9399%2E)
13. Michael Flor and Yoko Futagi. 2012. On using context for automatic correction of non-word misspellings in student essays. In Proceedings of the Seventh Workshop on Building Educational Applications Using NLP, pages 105–115, Montréal, Canada. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Michael+Flor+and+Yoko+Futagi%2E+2012%2E+On+using+context+for+automatic+correction+of+non%2Dword+misspellings+in+student+essays%2E+In+Proceedings+of+the+Seventh+Workshop+on+Building+Educational+Applications+Us)
14. Andrew Carlson and Ian Fette. 2007. Memory-based context-sensitive spelling correction at web scale. In Proceedings of the IEEE International Conference on Machine Learning and Applications (ICMLA). [find](https://scholar.google.com/scholar?q=Andrew+Carlson+and+Ian+Fette%2E+2007%2E+Memory%2Dbased+context%2Dsensitive+spelling+correction+at+web+scale%2E+In+Proceedings+of+the+IEEE+International+Conference+on+Machine+Learning+and+Applications+%28ICMLA%29%2E)
15. Qing Chen, Mu Li, and Ming Zhou. 2007. Improving query spelling correction using web search results. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pages 181–189, Prague, Czech Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Qing+Chen%2C+Mu+Li%2C+and+Ming+Zhou%2E+2007%2E+Improving+query+spelling+correction+using+web+search+results%2E+In+Proceedings+of+the+2007+Joint+Conference+on+Empirical+Methods+in+Natural+Language+Processing+and)
16. Michael Flor, Yoko Futagi, Melissa Lopez, and Matthew Mulholland. 2015. Patterns of misspellings in L2 and L1 English: a view from the ETS Spelling Corpus. In Learner Corpus Research: LCR2013 Conference Proceedings, volume 6 of Bergen Language and Linguistic Studies (BeLLS), pages 107–132. [↗](https://doi.org/10.15845/bells.v6i0.811)
17. Shamil Chollampatt and Hwee Tou Ng. 2018. A multi-layer convolutional encoder-decoder neural network for grammatical error correction. In Proceedings The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18). Association for the Advancement of Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Shamil+Chollampatt+and+Hwee+Tou+Ng%2E+2018%2E+A+multi%2Dlayer+convolutional+encoder%2Ddecoder+neural+network+for+grammatical+error+correction%2E+In+Proceedings+The+Thirty%2DSecond+AAAI+Conference+on+Artificial+In)
18. Matthias Hagen, Martin Potthast, Marcel Gohsen, Anja Rathgeber, and Benno Stein. 2017. A Large-Scale Query Spelling Correction Corpus. In 40th International ACM Conference on Research and Development in Information Retrieval (SIGIR 17), pages 1261–1264. ACM. [find](https://scholar.google.com/scholar?q=Matthias+Hagen%2C+Martin+Potthast%2C+Marcel+Gohsen%2C+Anja+Rathgeber%2C+and+Benno+Stein%2E+2017%2E+A+Large%2DScale+Query+Spelling+Correction+Corpus%2E+In+40th+International+ACM+Conference+on+Research+and+Development+)
19. Shamil Chollampatt, Kaveh Taghipour, and Hwee Tou Ng. 2016. [Neural network translation models for grammatical error correction](https://md.research.elamur.ai/free/en/papers/chollampatt-2016-neural-network-translation-models-grammatical/). In Proceedings of the Saša Hasan, Carmen Heger, and Saab Mansour. 2015. Spelling correction of user search queries through statistical machine translation. In Proceedings of the Tomoya Mizumoto and Ryo Nagata. 2017. Analyzing the Impact of Spelling Errors on POS-Tagging and Chunking in Learner English. In Proceedings of the 4th Workshop on Natural Language Processing Techniques for Educational Applications (NLPTEA 2017), pages 54–58, Taipei, Taiwan. Asian Federation of Natural Language Processing. 2015 Conference on Empirical Methods in Natural Language Processing, pages 451–460, Lisbon, Portugal. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.1606.00189)
20. Michael Heilman, Aoife Cahill, Nitin Madnani, Melissa Lopez, Matthew Mulholland, and Joel Tetreault. 2014. Predicting grammaticality on an ordinal scale. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 174– 180, Baltimore, Maryland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Michael+Heilman%2C+Aoife+Cahill%2C+Nitin+Madnani%2C+Melissa+Lopez%2C+Matthew+Mulholland%2C+and+Joel+Tetreault%2E+2014%2E+Predicting+grammaticality+on+an+ordinal+scale%2E+In+Proceedings+of+the+52nd+Annual+Meeting+of+t)
21. Ryo Nagata, Hiroya Takamura, and Graham Neubig. 2017. Adaptive Spelling Error Correction Models for Learner English. Procedia Computer Science, 112:474–483. [find](https://scholar.google.com/scholar?q=Ryo+Nagata%2C+Hiroya+Takamura%2C+and+Graham+Neubig%2E+2017%2E+Adaptive+Spelling+Error+Correction+Models+for+Learner+English%2E+Procedia+Computer+Science%2C+112%3A474%E2%80%93483%2E)
22. Ryo Nagata, Edward Whittaker, and Vera Sheinman. 2011. Creating a manually error-tagged and shallow-parsed learner corpus. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 1210–1219, Portland, Oregon, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ryo+Nagata%2C+Edward+Whittaker%2C+and+Vera+Sheinman%2E+2011%2E+Creating+a+manually+error%2Dtagged+and+shallow%2Dparsed+learner+corpus%2E+In+Proceedings+of+the+49th+Annual+Meeting+of+the+Association+for+Computationa)
23. Alistair E. W. Johnson, Tom J. Pollard, Lu Shen, Liwei H. Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo A. Celi, and Roger G. Mark. 2016. [MIMIC-III, a freely accessible critical care database](https://md.research.elamur.ai/free/en/papers/johnson-2016-mimic-iii-freely-accessible-critical/). Scientific Data, 3:160035+.
24. Mark D. Kernighan, Kenneth W. Church, and William A. Gale. 1990. [A spelling correction program based on a noisy channel model](https://md.research.elamur.ai/free/en/papers/kernighan-1990-spelling-correction-program-based-noisy/). In Papers presented to the 13th International Conference on Computational Linguistics (COLING 1990), volume 2, pages 205–210.
25. Courtney Napoles, Keisuke Sakaguchi, and Joel Tetreault. 2017. JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 229–234, Valencia, Spain. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.1702.04066)
26. Karen Kukich. 1992. Techniques for automatically correcting words in text. ACM Computing Surveys, 24:377–439. [↗](https://doi.org/10.1145/146370.146380)
27. Hwee Tou Ng, Siew Mei Wu, Ted Briscoe, Christian Hadiwinoto, Raymond Hendy Susanto, and Christopher Bryant. 2014. The CoNLL-2014 Shared Task on Grammatical Error Correction. In Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task, pages 1– 14, Baltimore, Maryland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Hwee+Tou+Ng%2C+Siew+Mei+Wu%2C+Ted+Briscoe%2C+Christian+Hadiwinoto%2C+Raymond+Hendy+Susanto%2C+and+Christopher+Bryant%2E+2014%2E+The+CoNLL%2D2014+Shared+Task+on+Grammatical+Error+Correction%2E+In+Proceedings+of+the+Eigh)
28. Kenneth H. Lai, Maxim Topaz, Foster R. Goss, and Li Zhou. 2015. Automated misspelling detection and correction in clinical free-text records. Journal of Biomedical Informatics, 15:188–195. [↗](https://doi.org/10.1016/j.jbi.2015.04.008)
29. Claudia Leacock and Martin Chodorow. 2003. C-rater: Automated scoring of short-answer questions. Computers and Humanities, 37:389–405. [↗](https://doi.org/10.1023/a:1025779619903)
30. Vladimir Levenshtein. 1966. Binary codes capable of correcting deletions, insertions and reversals. Soviet Physics Doklady, 10:707–710. [find](https://scholar.google.com/scholar?q=Vladimir+Levenshtein%2E+1966%2E+Binary+codes+capable+of+correcting+deletions%2C+insertions+and+reversals%2E+Soviet+Physics+Doklady%2C+10%3A707%E2%80%93710%2E)
31. Diane Nicholls. 2003. The Cambridge Learner Corpus – error coding and analysis for lexicography and ELT. In Proceedings of the Corpus Linguistics 2003 conference, pages 572–581. [find](https://scholar.google.com/scholar?q=Diane+Nicholls%2E+2003%2E+The+Cambridge+Learner+Corpus+%E2%80%93+error+coding+and+analysis+for+lexicography+and+ELT%2E+In+Proceedings+of+the+Corpus+Linguistics+2003+conference%2C+pages+572%E2%80%93581%2E)
32. Omer Levy and Yoav Goldberg. 2014. [Linguistic regularities in sparse and explicit word representations](https://md.research.elamur.ai/free/en/papers/levy-2014-linguistic-regularities-sparse-explicit-word/). In Proceedings of the Eighteenth Conference on Computational Natural Language Learning, pages 171–180, Ann Arbor, Michigan. Association for Computational Linguistics.
33. Jon Patrick, Mojtaba Sabbagh, Suvir Jain, and Haifeng Zheng. 2010. Spelling correction in clinical notes with emphasis on first suggestion accuracy. In 2nd Workshop on Building and Evaluating Resources for Biomedical Text Mining, pages 2–8. [find](https://scholar.google.com/scholar?q=Jon+Patrick%2C+Mojtaba+Sabbagh%2C+Suvir+Jain%2C+and+Haifeng+Zheng%2E+2010%2E+Spelling+correction+in+clinical+notes+with+emphasis+on+first+suggestion+accuracy%2E+In+2nd+Workshop+on+Building+and+Evaluating+Resource)
34. Lawrence Philips. 2000. The double-metaphone search algorithm. Dr. Dobb’s Journal. [find](https://scholar.google.com/scholar?q=Lawrence+Philips%2E+2000%2E+The+double%2Dmetaphone+search+algorithm%2E+Dr%2E+Dobb%E2%80%99s+Journal%2E)
35. Mu Li, Muhua Zhu, Yang Zhang, and Ming Zhou. 2006. Exploring distributional similarity based models for query spelling correction. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pages 1025–1032, Sydney, Australia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mu+Li%2C+Muhua+Zhu%2C+Yang+Zhang%2C+and+Ming+Zhou%2E+2006%2E+Exploring+distributional+similarity+based+models+for+query+spelling+correction%2E+In+Proceedings+of+the+21st+International+Conference+on+Computational+)
36. Alla Rozovskaya and Dan Roth. 2016. Grammatical error correction: Machine translation and classifiers. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2205–2215, Berlin, Germany. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Alla+Rozovskaya+and+Dan+Roth%2E+2016%2E+Grammatical+error+correction%3A+Machine+translation+and+classifiers%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volum)
37. Patrick Ruch, Robert Baud, and Antoine Geissbuḧler. 2003. Using lexical disambiguation and namedentity recognition to improve spelling correction in the electronic patient record. Artificial Intelligence in Medicine, 29:169–184. [find](https://scholar.google.com/scholar?q=Patrick+Ruch%2C+Robert+Baud%2C+and+Antoine+Geissbuh%CC%88ler%2E+2003%2E+Using+lexical+disambiguation+and+namedentity+recognition+to+improve+spelling+correction+in+the+electronic+patient+record%2E+Artificial+Intellig)
38. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S. Corrado, and Jeff Dean. 2013. [Distributed representations of words and phrases and their compositionality](https://md.research.elamur.ai/free/en/papers/mikolov-2013-distributed-representations-words-phrases-their/). In Advances in Neural Information Processing Systems, pages 3111–3119. [↗](https://doi.org/10.48550/arxiv.1310.4546)
39. Claude Shannon. 1948. A mathematical theory of communications. Bell Systems Technical Journal, 27:623–656. [find](https://scholar.google.com/scholar?q=Claude+Shannon%2E+1948%2E+A+mathematical+theory+of+communications%2E+Bell+Systems+Technical+Journal%2C+27%3A623%E2%80%93656%2E)
40. Jana Sukkarieh and John Blackmore. 2009. C-rater: Automatic content scoring for short constructed responses. In Proceedings of the 22nd International Florida Artificial Intelligence Research Society Conference, pages 290–295. [find](https://scholar.google.com/scholar?q=Jana+Sukkarieh+and+John+Blackmore%2E+2009%2E+C%2Drater%3A+Automatic+content+scoring+for+short+constructed+responses%2E+In+Proceedings+of+the+22nd+International+Florida+Artificial+Intelligence+Research+Society+C)
41. Kristina Toutanova and Robert Moore. 2002. [Pronunciation modeling for improved spelling correction](https://md.research.elamur.ai/free/en/papers/toutanova-2002-pronunciation-modeling-improved-spelling-correction/). In Proceedings of 40th Annual Meeting of the Association for Computational Linguistics, pages 144– 151, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics.
42. Kuansan Wang and Jan Pedersen. 2011. Review of MSR-Bing web scale speller challenge. In Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval (SIGIR 2011), pages 1339–1340. [find](https://scholar.google.com/scholar?q=Kuansan+Wang+and+Jan+Pedersen%2E+2011%2E+Review+of+MSR%2DBing+web+scale+speller+challenge%2E+In+Proceedings+of+the+34th+international+ACM+SIGIR+conference+on+Research+and+development+in+Information+Retrieval+)
43. Mark Warschauer and Paige Ware. 2006. Automated writing evaluation: Defining the classroom research agenda. Language Teaching Research, 10(2):157– 180. [↗](https://doi.org/10.1191/1362168806lr190oa)
44. Casey Whitelaw, Ben Hutchinson, Grace Y Chung, and Ged Ellis. 2009. Using the Web for language independent spellchecking and autocorrection. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 890– 899, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Casey+Whitelaw%2C+Ben+Hutchinson%2C+Grace+Y+Chung%2C+and+Ged+Ellis%2E+2009%2E+Using+the+Web+for+language+independent+spellchecking+and+autocorrection%2E+In+Proceedings+of+the+2009+Conference+on+Empirical+Methods+)
45. Amber Wilcox-O’Hearn, Graeme Hirst, and Alexander Budanitsky. 2008. Real-word Spelling Correction with Trigrams: A Reconsideration of the Mays, Damerau, and Mercer Model. In Proceedings of CICLing-2008, pages 605–616. [find](https://scholar.google.com/scholar?q=Amber+Wilcox%2DO%E2%80%99Hearn%2C+Graeme+Hirst%2C+and+Alexander+Budanitsky%2E+2008%2E+Real%2Dword+Spelling+Correction+with+Trigrams%3A+A+Reconsideration+of+the+Mays%2C+Damerau%2C+and+Mercer+Model%2E+In+Proceedings+of+CICLing%2D200)
46. Helen Yannakoudakis, Ted Briscoe, and Ben Medlock. 2011. [A New Dataset and Method for Automatically Grading ESOL Texts](https://md.research.elamur.ai/free/en/papers/yannakoudakis-2011-new-dataset-method-automatically-grading/). In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 180–189, Portland, Oregon, USA. Association for Computational Linguistics.

*Updated 1 November 2026*