1 / 37

Automated Identification of Preposition Errors

Automated Identification of Preposition Errors. Joel Tetreault Educational Testing Service ECOLT October 29, 2010. Outline. Computational Linguistics (CL) and Natural Language Processing (NLP) NLP at ETS (automated scoring) Automated Preposition Error Detection. Linguistics.

Download Presentation

Automated Identification of Preposition Errors

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Automated Identification of Preposition Errors Joel Tetreault Educational Testing Service ECOLT October 29, 2010

  2. Outline • Computational Linguistics (CL) and Natural Language Processing (NLP) • NLP at ETS (automated scoring) • Automated Preposition Error Detection

  3. Linguistics Homer talked to Marge D’oh!

  4. Computational Linguistics Want computers to understand language Homer talked to Marge D’oh!

  5. Computational Linguistics Homer talked to Marge D’oh! 9omer2 ta3lked4 6arge1

  6. Computational Linguistics vs. NLP • Computational Linguistics (CL): • Computers understanding language • Modeling how people communicate • Natural Language Processing (NLP): • Applications on the computer side • Natural: refers to languages spoken by people (English, Swahili) vs. artificial languages (C++) • Take CL theories and implement them into tools • CL and NLP often conflated

  7. Computational Linguistics Space CL • Computer Science: learning algorithms • Linguistics: formal grammars • Psychology: human processing modeling

  8. Computational Linguistics Space Artificial Intelligence CL • Perfect speech recognition • Perfect language understanding • Perfect speech synthesis • Perfect discourse modeling • Intention Recognition • World Knowledge • (Vision) Intelligent Machines

  9. Real World Applications of NLP • Spelling and Grammar correction/detection • MSWord, e-rater • Machine Translation • Google and Bing Translate • Opinion Mining • Extract sentiment of demographic from blogs and social media • Speech Recognition and Synthesis • Automatic Document Summarization

  10. NLP at ETS: Motivation • Millions of GRE and TOEFL tests taken each year • Tests move to more natural assessment • Fewer multiple choice questions • Tests have essay component • Problem: • Thousands of raters required • Costly and timely

  11. NLP at ETS • Use NLP techniques to automatically score essays (e-rater) • Other scoring tools which use NLP: • Criterion: online writing feedback • SpeechRater: automatic speaking assessment • C-Rater: content scoring of short answers • Plagiarism Detection

  12. E-rater (Automated Essay Scoring) • First deployed in 1999 for GMAT Writing Assessment • Operational for the GRE and TOEFL as well as a collection of smaller assessments • System Performance (5 point essay scale): • E-rater/Human agreement: 75% exact, 98% exact (+1 adjacent) • Comparable to two humans

  13. E-rater (Automated Essay Scoring) • Massive collection of 50+ weighted features organized into 5+ high level features • Each feature is represented by a module: • Simple: collection of manual rules and/or regular expressions • More complex: NLP (Natural Language Processing) statistical system is behind the feature • Combined using linear regression

  14. E-rater Features

  15. E-rater Features

  16. How to Game the System  • Word Salad Detector • Unusually Short / Off-Topic Essays • “Quick The the over brown dogs fox. Jumped. Lazy” • “Skfhdorla;sf[e’skasas,fr’r;/.,fkrasa” • “I don’t know how to explain this question because I took a nap. Sorry.” • “I THINK EVERYONE SHOULD BE ABLE TO WEAR WHATEVER THE HELL THEY WANT TO WEAR.”

  17. NLP for English Language Learners • Increasing need for tools for instruction in English as a Second Language (ESL) • 300 million ESL learners in China alone • 10% of US students learn English as a second language • Teachers now burdened with teaching classes with wildly varying levels of English fluency • Assessments for EFL Teacher Proficiency

  18. NLP for English Language Learners • Other Interest: • Microsoft Research (ESL Assistant) • Publishing/Assessment Companies (Cambridge, Oxford, Pearson) • Universities

  19. Objective • Research Goal: develop NLP tools to automatically provide feedback to ESL learners about grammatical errors • Preposition Error Detection • Selection Error (“They arrived to the town.”) • Extraneous Use (“They came to outside.”) • Omitted (“He is fond this book.”)

  20. Motivation • Preposition usage is one of the most difficult aspects of English for non-native speakers • [Dalgish ’85] – 18% of sentences from ESL essays contain a preposition error • Our data: 8-10% of all prepositions in TOEFL essays are used incorrectly

  21. Why are prepositions hard to master? • Prepositions are problematic because they can perform so many complex roles • Preposition choice in an adjunct is constrained by its object (“on Friday”, “at noon”) • Prepositions are used to mark the arguments of a predicate (“fond of beer.”) • Phrasal Verbs (“give into their demands.”) • “give in”  “acquiesce, surrender”

  22. Why are prepositions hard to master? • Multiple prepositions can appear in the same context: “When the plant is horizontal, the force of the gravity causes the sap to move __ the underside of the stem.”

  23. Preposition Error Detection • In NLP: computer system learns from lots and lots of data • Training Phase: Create a “model” of the problem area • Face detection • Credit Card Usage • Translating from Chinese to English • Testing Phase: Use model to classify new cases

  24. Baseball Feature Example • Predict the outcome of the baseball game • Look at all the games where both teams played each other: • For each game (event), use features: • Win/loss records before game • Home field advantage • Players’ prior performance • Train learning algorithm

  25. Baseball Feature Example

  26. Building a Model of Preposition Usage • Prepositions are influenced by: • Words in the local context, and how they interact with each other (lexical) • Syntactic structure of context • Semantic interpretation • Get computer to understand correct usage: • Encode these influences as “features” • Train computer algorithm on millions of examples of correct usage with the associated features

  27. Deriving the Features • Derived using NLP tools • Tokenizing • “He is fond of beer . ” • Part-of-Speech Tagging • “ He_PRPis_BEfond_VBof_PREPbeer_NN ._.” • Chunking / Parsing • “ {NP He_PRP } {VP is_BEfond_VB } of_PREP{NP beer_NN } ._.”

  28. Feature Overview • System uses a minimum of 25 features • Lexical, syntactic, semantic sources • Head words before and after preposition • Words in the local context (+/- 2 words) • Part of Speech (POS) of words above • Combination Features • Parse Features

  29. Preposition Feature Example • He is fond of beer. • The train will arrive at the Springfield Station. • The car with the broken wheel is in the shop.

  30. Flagging Errors • Train learning algorithm on millions of events  develop model (classifier) • Testing (flagging errors) • Derive features • Replace writer’s preposition with all other prepositions, classifier outputs score for each preposition • Compare top scoring preposition to score of writer’s preposition

  31. Thresholds FLAG AS ERROR “He is fond withbeer”

  32. Thresholds FLAG AS OK “My sister usually gets home by3:00”

  33. Performance • Evaluation corpus of 5600 TOEFL essays (8200 prepositions) • Each preposition manually annotated • Recall = 0.19 ; Precision = 0.84 • 1/5 of errors are flagged • 84% of flagged errors are indeed errors • Precision > recall to reduce false positives • State of the Art performance

  34. Conclusions • Presented an overview of: • NLP • NLP at ETS • One feature (Prepositions) in e-rater • Future Directions • Use of large scale corpora (WWW) • L1-specific models • Train on error-annotated data

  35. Plugs • ETS/NLP Publications: • http://ets.org/research/erater.html • 5th Workshop on Innovative Use of NLP for Educational Applications (NAACL-10) • http://www.cs.rochester.edu/u/tetreaul/naacl-bea5.html

  36. Plugs • “Automated Grammatical Error Detection for Language Learners” • Leacock et al., 2010 • Synthesis Series

  37. Thanks! Joel Tetreault: JTetreault@ets.org

More Related