Automated Grammatical Error Detection for Language Learners

✍ Scribed by Claudia Leacock, Martin Chodorow, Michael Gamon, Joel Tetreault, Graeme Hirst

• Publisher: Morgan and Claypool Publishers
• Year: 2010
• Tongue: English
• Leaves: 134
• Series: Synthesis Lectures on Human Language Technologies
• Category: Library

✦ Synopsis

It has been estimated that over a billion people are using or learning English as a second or foreign language, and the numbers are growing not only for English but for other languages as well. These language learners provide a burgeoning market for tools that help identify and correct learners' writing errors. Unfortunately, the errors targeted by typical commercial proofreading tools do not include those aspects of a second language that are hardest to learn. This volume describes the types of constructions English language learners find most difficult -- constructions containing prepositions, articles, and collocations. It provides an overview of the automated approaches that have been developed to identify and correct these and other classes of learner errors in a number of languages. Error annotation and system evaluation are particularly important topics in grammatical error detection because there are no commonly accepted standards. Chapters in the book describe the options available to researchers, recommend best practices for reporting results, and present annotation and evaluation schemes. The final chapters explore recent innovative work that opens new directions for research. It is the authors' hope that this volume will contribute to the growing interest in grammatical error detection by encouraging researchers to take a closer look at the field and its many challenging problems. Table of Contents: Introduction / History of Automated Grammatical Error Detection / Special Problems of Language Learners / Language Learner Data / Evaluating Error Detection Systems / Article and Preposition Errors / Collocation Errors / Different Approaches for Different Errors / Annotating Learner Errors / New Directions / Conclusion

✦ Table of Contents

Acknowledgments......Page 11
Working Definition of Grammatical Error......Page 13
Automated grammatical error detection: NLP and CALL......Page 14
Outline......Page 15
In the Beginning: From Pattern Matching to Parsing......Page 17
Introduction to Data-Driven and Hybrid Approaches......Page 23
Errors Made by English Language Learners......Page 27
The Influence of L1......Page 31
The English Preposition System......Page 32
The English Article System......Page 35
English Collocations......Page 36
Summary......Page 38
Learner Corpora......Page 39
Non-English Learner Corpora......Page 43
Using Artificially Created Error Corpora......Page 44
Using Well-Formed Corpora......Page 46
Evaluating Error Detection Systems......Page 49
Evaluation Using a Corpus of Correct Usage......Page 50
Verifying Results on Learner Writing......Page 52
Evaluation on Fully-Annotated Learner Corpora......Page 53
Using Multiple Raters for Evaluation......Page 55
Checklist for Consistent Reporting of System Results......Page 56
Summary......Page 57
Overview......Page 59
Articles......Page 60
Prepositions......Page 66
Two end-to-end systems: Criterion and MSR ESL Assistant......Page 69
Defining Collocations......Page 75
Measuring the Strength of Association between Words......Page 76
Systems for Detecting and Correcting Collocation Errors......Page 80
Detection of Ungrammatical Sentences......Page 85
Heuristic Rule-based Approaches......Page 86
More Complex Verb Form Errors......Page 89
Spelling Errors......Page 90
Summary......Page 91
Number of Raters......Page 93
How to Correct an Error......Page 94
Annotation Approaches......Page 95
Examples of Comprehensive Annotation Schemes......Page 96
Example of a Targeted Annotation Scheme......Page 97
Sampling Approach with Multiple Annotators......Page 98
Amazon Mechanical Turk......Page 99
Summary......Page 102
Recent Innovations in Error Detection......Page 103
Using the Web......Page 104
Using the Google N-Gram Corpus......Page 106
Using Machine Translation to Correct Errors......Page 107
Leveraging L1 Tendencies with Region Web Counts......Page 108
Longitudinal Studies......Page 109
Conclusion......Page 113
Bibliography......Page 115
Authors' Biographies......Page 133