---
title: "‘Calling on the classical phone': a distributional model of"
description: "The paper tackles detecting wrong adjective choices in English written by learners… 81% accuracy. 42 references, cited by 1 paper here."
authors: ["Aurélie Herbelot", "Ekaterina Kochmar"]
year: 2016
venue: "Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers"
source: "https://aclanthology.org/C16-1093/"
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/herbelot-2016-calling-classical-phone-distributional-model/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/herbelot-2016-calling-classical-phone-distributional-model/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2016](https://md.research.elamur.ai/free/en/papers/2016/page/5/) / ‘Calling on the classical phone': a distributional model of adjective-noun errors in learners' English

# ‘Calling on the classical phone': a distributional model of adjective-noun errors in learners' English

**Authors:** [Aurélie Herbelot](https://md.research.elamur.ai/free/en/authors/aurelie-herbelot/) and [Ekaterina Kochmar](https://md.research.elamur.ai/free/en/authors/ekaterina-kochmar/) · **Year:** 2016 · **Venue:** [Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers](https://md.research.elamur.ai/free/en/venues/coling/) ([COLING 2016](https://md.research.elamur.ai/free/en/venues/coling/2016/)) · **Publisher:** [International Committee on Computational Linguistics (ICCL)](https://md.research.elamur.ai/free/en/publishers/international-committee-on-computational-linguistics-iccl/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/C16-1093/) · [PDF](https://aclanthology.org/C16-1093.pdf) · [OpenAlex](https://openalex.org/W2573371028)

**Citations:** 4 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper tackles detecting wrong adjective choices in English written by learners, where an adjective is misused in its context of use (e.g. *classical phone*). Content-word errors are hard because, unlike function words, they have no closed set of likely confusions. Building on Kochmar and Briscoe (K&B), whose system judges AN pairs out of context, the authors add a context-sensitive component based on distributional topic coherence. Coherence is the mean pairwise cosine similarity among the words around an AN, computed in a PPMI-weighted BNC vector space. The intuition is that a misused adjective lowers how well a sentence hangs together semantically. The coherence features feed an SVM, tested on the K&B AN dataset drawn from the Cambridge Learner Corpus. Adding adjective-specific information helps, and combining the system with the out-of-context classifier helps further. The authors conclude that errors should be modelled per adjective class. They also show that artificially generated errors cannot replace real learner data for this task.

## Key points
- The data is the K&B AN dataset: 798 ANs taken from CLC that are unattested in the BNC, annotated both out of context (OOC) and in context (IC). The authors use 824 of its 892 contexts. The majority baseline is 0.55, and inter-annotator agreement (the upper bound) is 0.74.
- The distributional space is built from the BNC using lemmatised 10-word windows, takes its dimensions from the 2000 content words that occur most often, and applies PPMI weighting. Context words are restricted to nouns, verbs, adjectives and adverbs.
- Three COH features alone give about 0.58–0.59 SVM accuracy. Adding an adjective feature raises this to as much as 0.66, with a 2-word context on each side.
- K&B's OOC system reaches 81% accuracy but falls to 65% when judged against in-context labels. Merging the OOC and IC features gives 68%, and a voting scheme reaches an upper bound close to human agreement.
- Synthetic errors were created by randomly swapping adjectives across 2-word context windows taken from 1M tokens of ukWaC parsed with RASP. Training on this data lowered accuracy to 56%.

## Interesting ideas
- Spotting an anomalous word by measuring how much it reduces the average pairwise similarity of its sentence neighbours is cheap, needs no confusion set, and can be explained as "this word does not fit its context".
- Kept separate, an out-of-context plausibility check and an in-context coherence check capture different signals, and combining them works only when the first stage has enough recall.
- Performance differs by adjective, so classifiers or thresholds specific to each lexical class can beat a single global model.
- Random substitution yields "errors" that do not resemble real mistakes, so synthetic negatives can mislead training for semantic tasks.
- The motivating example (*classical phone* where the writer meant *landline*) shows that the intended word may not be a near neighbour of the error, so detection should not depend on proposing a correction.

## For Mova

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

- **I1** (frames): Low coherence between a predicate's argument and its surrounding content words could flag a likely misused word or a figurative reading before semantic roles are fixed.
- **I2** (world): Knowledge-graph plausibility checks on attribute–entity pairs could run first, with context coherence deciding the borderline cases, provided the first stage does not miss too many.
- **I3** (learn): Evaluation and repair-rule induction could be broken down by lemma or class to expose words on which a general model quietly fails.
- **I4** (learn): Self-play or synthetic negative controls for lexical-semantic checks should be validated against real human errors before being trusted as training data.
- **I5** (answer): Graders of student text could flag a word as not fitting its context without being forced to offer a specific replacement.

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

## Institutions

- [University of Cambridge](https://md.research.elamur.ai/free/en/universities/university-of-cambridge/) — University, Cambridge, United Kingdom · 256 works · 123,373 citations
- [University of Trento](https://md.research.elamur.ai/free/en/universities/university-of-trento/) — University, Trento, Italy · 87 works · 15,761 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Developmental and Educational Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/developmental-and-educational-psychology/) · 523 works

🧭 Topics (1): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,379 works

## Cite

Cite as: Aurélie Herbelot and Ekaterina Kochmar. 2016. ‘Calling on the classical phone': a distributional model of adjective-noun errors in learners' English. Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers.

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

```bibtex
@inproceedings{herbelot2016calling,
  title = {{‘Calling on the classical phone': a distributional model of adjective-noun errors in learners' English}},
  author = {Aurélie Herbelot and Ekaterina Kochmar},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  year = {2016},
  doi = {10.17863/cam.9931},
  url = {https://doi.org/10.17863/cam.9931}
}
```

- [← previous The Inner Circle vs. the Outer Circle or British English vs. American English](https://md.research.elamur.ai/free/en/papers/lee-2016-inner-circle-vs-outer-circle/)
- [next → ‘Who would have thought of that!': A Hierarchical Topic Model for Extraction of Sarcasm-prevalent Topics and Sarcasm Detection](https://md.research.elamur.ai/free/en/papers/joshi-2016-who-would-have-thought-that/)
- [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/page/5/)

## References

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

1. Loulwah AlSumait, Daniel Barbará, James Gentle, and Carlotta Domeniconi. 2009. Topic significance ranking of LDA generative models. In Machine Learning and Knowledge Discovery in Databases, pages 67–82. Springer. [find](https://scholar.google.com/scholar?q=Loulwah+AlSumait%2C+Daniel+Barbara%CC%81%2C+James+Gentle%2C+and+Carlotta+Domeniconi%2E+2009%2E+Topic+significance+ranking+of+LDA+generative+models%2E+In+Machine+Learning+and+Knowledge+Discovery+in+Databases%2C+pages+67%E2%80%93)
2. Øistein E. Andersen, Helen Yannakoudakis, Fiona Barker, and Tim Parish. 2013. Developing and testing a self-assessment and tutoring system. In Proceedings of the BEA-2013, pages 32–41. [find](https://scholar.google.com/scholar?q=%C3%98istein+E%2E+Andersen%2C+Helen+Yannakoudakis%2C+Fiona+Barker%2C+and+Tim+Parish%2E+2013%2E+Developing+and+testing+a+self%2Dassessment+and+tutoring+system%2E+In+Proceedings+of+the+BEA%2D2013%2C+pages+32%E2%80%9341%2E)
3. Marco Baroni, Silvia Bernardini, Adriano Ferraresi, and Eros Zanchetta. 2009. The WaCky wide web: a collection of very large linguistically processed web-crawled corpora. Language resources and evaluation, 43(3):209–226. [↗](https://doi.org/10.1007/s10579-009-9081-4)
4. Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural Language Processing with Python – Analyzing Text with the Natural Language Toolkit. O’Reilly Media. [find](https://scholar.google.com/scholar?q=Steven+Bird%2C+Ewan+Klein%2C+and+Edward+Loper%2E+2009%2E+Natural+Language+Processing+with+Python+%E2%80%93+Analyzing+Text+with+the+Natural+Language+Toolkit%2E+O%E2%80%99Reilly+Media%2E)
5. Ted Briscoe, John Carroll, and Rebecca Watson. 2006. [The second release of the RASP system](https://md.research.elamur.ai/free/en/papers/briscoe-2006-second-release-rasp-system/). In Proceedings of the COLING/ACL on Interactive presentation sessions, pages 77–80.
6. Yu-Chia Chang, Jason S. Chang, Hao-Jan Chen, and Hsien-Chin Liou. 2008. An automatic collocation writing assistant for Taiwanese EFL learners: A case of corpus-based NLP technology. Computer Assisted Language Learning, 21(3):283–299. [↗](https://doi.org/10.1080/09588220802090337)
7. Jonathan Chang, Sean Gerrish, Chong Wang, Jordan L Boyd-graber, and David M Blei. 2009. [Reading tea leaves: How humans interpret topic models](https://md.research.elamur.ai/free/en/papers/chang-2009-reading-tea-leaves-humans-interpret-topic/). In Advances in neural information processing systems, pages 288–296.
8. Martin Chodorow, Michael Gamon, and Joel Tetreault. 2010. The utility of grammatical error detection systems for English language learners: Feedback and Assessment. Language Testing, 27(3):335–353. [find](https://scholar.google.com/scholar?q=Martin+Chodorow%2C+Michael+Gamon%2C+and+Joel+Tetreault%2E+2010%2E+The+utility+of+grammatical+error+detection+systems+for+English+language+learners%3A+Feedback+and+Assessment%2E+Language+Testing%2C+27%283%29%3A335%E2%80%93353%2E)
9. Daniel Dahlmeier and Hwee Tou Ng. 2011a. Correcting Semantic Collocation Errors with L1-induced Paraphrases. In Proceedings of the EMNLP-2011, pages 107–117. [find](https://scholar.google.com/scholar?q=Daniel+Dahlmeier+and+Hwee+Tou+Ng%2E+2011a%2E+Correcting+Semantic+Collocation+Errors+with+L1%2Dinduced+Paraphrases%2E+In+Proceedings+of+the+EMNLP%2D2011%2C+pages+107%E2%80%93117%2E)
10. Daniel Dahlmeier and Hwee Tou Ng. 2011b. Grammatical error correction with alternating structure optimization. In Proceedings of the ACL-HLT 2011, pages 915–923. [find](https://scholar.google.com/scholar?q=Daniel+Dahlmeier+and+Hwee+Tou+Ng%2E+2011b%2E+Grammatical+error+correction+with+alternating+structure+optimization%2E+In+Proceedings+of+the+ACL%2DHLT+2011%2C+pages+915%E2%80%93923%2E)
11. Robert Dale and Adam Kilgarriff. 2011. [Helping Our Own: The HOO 2011 Pilot Shared Task](https://md.research.elamur.ai/free/en/papers/dale-2011-helping-our-own-hoo-2011/). In Proceedings of the 13th European Workshop on Natural Language Generation, pages 242–249.
12. Robert Dale, Ilya Anisimoff, and George Narroway. 2012. [HOO 2012: A Report on the Preposition and Determiner Error Correction Shared Task](https://md.research.elamur.ai/free/en/papers/dale-2012-hoo-2012-report-preposition-determiner/). In Proceedings of the BEA-2012, pages 54–62.
13. Vidas Daudaravicius, Rafael E. Banchs, Elena Volodina, and Courtney Napoles. 2016. A Report on the Automatic Evaluation of Scientific Writing Shared Task. In Proceedings of the BEA-2016. [find](https://scholar.google.com/scholar?q=Vidas+Daudaravicius%2C+Rafael+E%2E+Banchs%2C+Elena+Volodina%2C+and+Courtney+Napoles%2E+2016%2E+A+Report+on+the+Automatic+Evaluation+of+Scientific+Writing+Shared+Task%2E+In+Proceedings+of+the+BEA%2D2016%2E)
14. Georgiana Dinu, Nghia The Pham, and Marco Baroni. 2013. General estimation and evaluation of compositional distributional semantic models. In Workshop on Continuous Vector Space Models and their Compositionality, pages 50–58, Sofia, Bulgaria. [find](https://scholar.google.com/scholar?q=Georgiana+Dinu%2C+Nghia+The+Pham%2C+and+Marco+Baroni%2E+2013%2E+General+estimation+and+evaluation+of+compositional+distributional+semantic+models%2E+In+Workshop+on+Continuous+Vector+Space+Models+and+their+Compo)
15. Rachele De Felice and Stephen G. Pulman. 2008. [A classifier-based approach to preposition and determiner error correction in L2 English](https://md.research.elamur.ai/free/en/papers/felice-2008-classifier-based-approach-preposition-determiner/). In Proceedings of the COLING-2008, pages 169–176.
16. Mariano Felice and Zheng Yuan. 2014. Generating artificial errors for grammatical error correction. In Proceedings of the Student Research Workshop at the ACL-2014, pages 116–126. [find](https://scholar.google.com/scholar?q=Mariano+Felice+and+Zheng+Yuan%2E+2014%2E+Generating+artificial+errors+for+grammatical+error+correction%2E+In+Proceedings+of+the+Student+Research+Workshop+at+the+ACL%2D2014%2C+pages+116%E2%80%93126%2E)
17. Mariano Felice, Zheng Yuan, Øistein E. Andersen, Helen Yannakoudakis, and Ekaterina Kochmar. 2014. Grammatical error correction using hybrid systems and type filtering. In Proceedings of the CoNLL 2014: Shared Task. [find](https://scholar.google.com/scholar?q=Mariano+Felice%2C+Zheng+Yuan%2C+%C3%98istein+E%2E+Andersen%2C+Helen+Yannakoudakis%2C+and+Ekaterina+Kochmar%2E+2014%2E+Grammatical+error+correction+using+hybrid+systems+and+type+filtering%2E+In+Proceedings+of+the+CoNLL+201)
18. Jennifer Foster and Øistein E Andersen. 2009. Generrate: generating errors for use in grammatical error detection. In Proceedings of the BEA-2009, pages 82–90. [find](https://scholar.google.com/scholar?q=Jennifer+Foster+and+%C3%98istein+E+Andersen%2E+2009%2E+Generrate%3A+generating+errors+for+use+in+grammatical+error+detection%2E+In+Proceedings+of+the+BEA%2D2009%2C+pages+82%E2%80%9390%2E)
19. Yoko Futagi, Paul Deane, Martin Chodorow, and Joel Tetreault. 2008. A computational approach to detecting collocation errors in the writing of non-native speakers of English. Computer Assisted Language Learning, 21(4):353–367. [↗](https://doi.org/10.1080/09588220802343561)
20. Michael Gamon, Jianfeng Gao, Chris Brockett, Alexander Klementiev, William Dolan, Dmitriy Belenko, and Lucy Vanderwende. 2008. [Using contextual speller techniques and language modeling for ESL error correction](https://md.research.elamur.ai/free/en/papers/gamon-2008-contextual-speller-techniques-language-modeling/). In Proceedings of IJCNLP-2008, pages 491–511.
21. Michael Gamon. 2010. Using mostly native data to correct errors in learners’ writing. In Proceedings of the NAACL-2010, pages 163–171. [find](https://scholar.google.com/scholar?q=Michael+Gamon%2E+2010%2E+Using+mostly+native+data+to+correct+errors+in+learners%E2%80%99+writing%2E+In+Proceedings+of+the+NAACL%2D2010%2C+pages+163%E2%80%93171%2E)
22. Carl James. 1998. Errors in Language Learning and Use: Exploring Error Analysis. London: Longman. [find](https://scholar.google.com/scholar?q=Carl+James%2E+1998%2E+Errors+in+Language+Learning+and+Use%3A+Exploring+Error+Analysis%2E+London%3A+Longman%2E)
23. Thorsten Joachims, 1999. Making Large-Scale SVM Learning Practical. Advances in Kernel Methods - Support Vector Learning, B. Schölkopf and C. Burges and A. Smola (ed.), MIT-Press. [↗](https://doi.org/10.17877/de290r-14262)
24. Marcin Junczys-Dowmunt and Roman Grundkiewicz. 2014. The AMU system in the CoNLL-2014 shared task: Grammatical error correction by data-intensive and feature-rich statistical machine translation. In Proceedings of the CoNLL-2014: Shared Task. [find](https://scholar.google.com/scholar?q=Marcin+Junczys%2DDowmunt+and+Roman+Grundkiewicz%2E+2014%2E+The+AMU+system+in+the+CoNLL%2D2014+shared+task%3A+Grammatical+error+correction+by+data%2Dintensive+and+feature%2Drich+statistical+machine+translation%2E+In+P)
25. Ekaterina Kochmar and Ted Briscoe. 2014. Detecting learner errors in the choice of content words using compositional distributional semantics. In Proceedings of the COLING-2014, pages 1740–1751. [find](https://scholar.google.com/scholar?q=Ekaterina+Kochmar+and+Ted+Briscoe%2E+2014%2E+Detecting+learner+errors+in+the+choice+of+content+words+using+compositional+distributional+semantics%2E+In+Proceedings+of+the+COLING%2D2014%2C+pages+1740%E2%80%931751%2E)
26. Claudia Leacock and Martin Chodorow, 2003. Automated Grammatical Error Detection. In M. D. Shermis and J. C. Burstein (eds.), Automated Essay Scoring: A Cross-Disciplinary Perspective, pages 195–207. Mahwah, NJ: Lawrence Erlbaum Associates. [find](https://scholar.google.com/scholar?q=Claudia+Leacock+and+Martin+Chodorow%2C+2003%2E+Automated+Grammatical+Error+Detection%2E+In+M%2E+D%2E+Shermis+and+J%2E+C%2E+Burstein+%28eds%2E%29%2C+Automated+Essay+Scoring%3A+A+Cross%2DDisciplinary+Perspective%2C+pages+195%E2%80%93207%2E+)
27. Claudia Leacock, Michael Gamon, and Chris Brockett. 2009. User Input and Interactions on Microsoft Research ESL Assistant. In Proceedings of the BEA-2009, pages 73–81. [find](https://scholar.google.com/scholar?q=Claudia+Leacock%2C+Michael+Gamon%2C+and+Chris+Brockett%2E+2009%2E+User+Input+and+Interactions+on+Microsoft+Research+ESL+Assistant%2E+In+Proceedings+of+the+BEA%2D2009%2C+pages+73%E2%80%9381%2E)
28. Claudia Leacock, Martin Chodorow, Michael Gamon, and Joel Tetreault. 2014. Automated Grammatical Error Detection for Language Learners, Second Edition. Synthesis Lectures on Human Language Technologies. Morgan and Claypool Publishers. [↗](https://doi.org/10.2200/s00562ed1v01y201401hlt025)
29. Anne Li-E Liu, David Wible, and Nai-Lung Tsao. 2009. Automated suggestions for miscollocations. In Proceedings of the BEA-2009, pages 47–50. [find](https://scholar.google.com/scholar?q=Anne+Li%2DE+Liu%2C+David+Wible%2C+and+Nai%2DLung+Tsao%2E+2009%2E+Automated+suggestions+for+miscollocations%2E+In+Proceedings+of+the+BEA%2D2009%2C+pages+47%E2%80%9350%2E)
30. David Mimno, Hanna M Wallach, Edmund Talley, Miriam Leenders, and Andrew McCallum. 2011. [Optimizing semantic coherence in topic models](https://md.research.elamur.ai/free/en/papers/mimno-2011-optimizing-semantic-coherence-topic-models/). In Proceedings of the EMNLP-2011, pages 262–272.
31. Jeff Mitchell and Mirella Lapata. 2008. Vector-based models of semantic composition. In Proceedings of ACL-HLT 2008, pages 236–244. [find](https://scholar.google.com/scholar?q=Jeff+Mitchell+and+Mirella+Lapata%2E+2008%2E+Vector%2Dbased+models+of+semantic+composition%2E+In+Proceedings+of+ACL%2DHLT+2008%2C+pages+236%E2%80%93244%2E)
32. David Newman, Jey Han Lau, Karl Grieser, and Timothy Baldwin. 2010. [Automatic evaluation of topic coherence](https://md.research.elamur.ai/free/en/papers/newman-2010-automatic-evaluation-topic-coherence/). In Proceedings of the NAACL-HLT 2010, pages 100–108.
33. Hwee Tou Ng, Siew Mei Wu, Yuanbin Wu, Christian Hadiwinoto, and Joel Tetreault. 2013. The CoNLL-2013 Shared Task on Grammatical Error Correction. In Proceedings of the CoNLL-2013: Shared Task, pages 1–12. [find](https://scholar.google.com/scholar?q=Hwee+Tou+Ng%2C+Siew+Mei+Wu%2C+Yuanbin+Wu%2C+Christian+Hadiwinoto%2C+and+Joel+Tetreault%2E+2013%2E+The+CoNLL%2D2013+Shared+Task+on+Grammatical+Error+Correction%2E+In+Proceedings+of+the+CoNLL%2D2013%3A+Shared+Task%2C+pages+1)
34. 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 CoNLL-2014: Shared Task, pages 1–14. [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+CoNL)
35. Taehyun Park, Edward Lank, Pascal Poupart, and Michael Terry. 2008. Is the sky pure today? AwkChecker: an assistive tool for detecting and correcting collocation errors. In Proceedings of the 21st annual ACM symposium on User interface software and technology, pages 121–130. [find](https://scholar.google.com/scholar?q=Taehyun+Park%2C+Edward+Lank%2C+Pascal+Poupart%2C+and+Michael+Terry%2E+2008%2E+Is+the+sky+pure+today%3F+AwkChecker%3A+an+assistive+tool+for+detecting+and+correcting+collocation+errors%2E+In+Proceedings+of+the+21st+ann)
36. Alla Rozovskaya and Dan Roth. 2010a. Annotating ESL errors: Challenges and rewards. In Proceedings of the BEA-2010, pages 28–36. [find](https://scholar.google.com/scholar?q=Alla+Rozovskaya+and+Dan+Roth%2E+2010a%2E+Annotating+ESL+errors%3A+Challenges+and+rewards%2E+In+Proceedings+of+the+BEA%2D2010%2C+pages+28%E2%80%9336%2E)
37. Alla Rozovskaya and Dan Roth. 2010b. Training paradigms for correcting errors in grammar and usage. In Proceedings of the NAACL-HLT 2010. [find](https://scholar.google.com/scholar?q=Alla+Rozovskaya+and+Dan+Roth%2E+2010b%2E+Training+paradigms+for+correcting+errors+in+grammar+and+usage%2E+In+Proceedings+of+the+NAACL%2DHLT+2010%2E)
38. Alla Rozovskaya, Dan Roth, and Vivek Srikumar. 2014. Correcting Grammatical Verb Errors. In Proceedings of EACL-2014, pages 358–367. [find](https://scholar.google.com/scholar?q=Alla+Rozovskaya%2C+Dan+Roth%2C+and+Vivek+Srikumar%2E+2014%2E+Correcting+Grammatical+Verb+Errors%2E+In+Proceedings+of+EACL%2D2014%2C+pages+358%E2%80%93367%2E)
39. Mark Steyvers and Tom Griffiths. 2007. Probabilistic topic models. In T. Landauer, D. McNamara, S. Dennis, and W. Kintsch, editors, Latent Semantic Analysis: A Road to Meaning. [find](https://scholar.google.com/scholar?q=Mark+Steyvers+and+Tom+Griffiths%2E+2007%2E+Probabilistic+topic+models%2E+In+T%2E+Landauer%2C+D%2E+McNamara%2C+S%2E+Dennis%2C+and+W%2E+Kintsch%2C+editors%2C+Latent+Semantic+Analysis%3A+A+Road+to+Meaning%2E)
40. Joel Tetreault, Jennifer Foster, and Martin Chodorow. 2010. Using parse features for preposition selection and error detection. In Proceedings of the ACL-2010: Short Papers, pages 353–358. [find](https://scholar.google.com/scholar?q=Joel+Tetreault%2C+Jennifer+Foster%2C+and+Martin+Chodorow%2E+2010%2E+Using+parse+features+for+preposition+selection+and+error+detection%2E+In+Proceedings+of+the+ACL%2D2010%3A+Short+Papers%2C+pages+353%E2%80%93358%2E)
41. Peter D. Turney and Patrick Pantel. 2010. [From frequency to meaning: Vector space models of semantics](https://md.research.elamur.ai/free/en/papers/turney-2010-frequency-meaning-vector-space-models/). Journal of Artificial Intelligence Research, 37:141–188. [↗](https://doi.org/10.1613/jair.2934)
42. Xing Yi, Jianfeng Gao, and William B. Dolan. 2008. A Web-based English Proofing System for English as a Second Language Users. In Proceedings of the IJCNLP-2008, pages 619–624. [find](https://scholar.google.com/scholar?q=Xing+Yi%2C+Jianfeng+Gao%2C+and+William+B%2E+Dolan%2E+2008%2E+A+Web%2Dbased+English+Proofing+System+for+English+as+a+Second+Language+Users%2E+In+Proceedings+of+the+IJCNLP%2D2008%2C+pages+619%E2%80%93624%2E)

*Updated 1 November 2026*