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

Slides:



Advertisements
Similar presentations
School of something FACULTY OF OTHER School of Computing FACULTY OF ENGINEERING Chunking: Shallow Parsing Eric Atwell, Language Research Group.
Advertisements

Introduction to Computational Linguistics
Chapter 4 Key Concepts.
Introduction to: Automated Essay Scoring (AES) Anat Ben-Simon Introduction to: Automated Essay Scoring (AES) Anat Ben-Simon National Institute for Testing.
Communicative Language Teaching (Classroom Activities)
Electronic Essay Graders Jay Lubomirski.  How electronic essay graders evaluate writing samples  Comparing the electronic graders to the human graders.
The Ups and Downs of Preposition Error Detection in ESL Writing Joel Tetreault[Educational Testing Service]
A method for unsupervised broad-coverage lexical error detection and correction 4th Workshop on Innovative Uses of NLP for Building Educational Applications.
® Towards Using Structural Events To Assess Non-Native Speech Lei Chen, Joel Tetreault, Xiaoming Xi Educational Testing Service (ETS) The 5th Workshop.
Introduction.  “a technique that enables the computer to encode complex grammatical knowledge such as humans use to assemble sentences, recognize errors.
INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE PROCESSING NLP-AI IIIT-Hyderabad CIIL, Mysore ICON DECEMBER, 2003.
HOO 2012: A Report on the Preposition and Determiner Error Correction Shared Task Robert Dale, Ilya Anisimoff and George Narroway Centre for Language Technology.
1 A Comparative Evaluation of Deep and Shallow Approaches to the Automatic Detection of Common Grammatical Errors Joachim Wagner, Jennifer Foster, and.
1 Developing Statistic-based and Rule-based Grammar Checkers for Chinese ESL Learners Howard Chen Department of English National Taiwan Normal University.
Confidential and Proprietary. Copyright © 2010 Educational Testing Service. All rights reserved. Catherine Trapani Educational Testing Service ECOLT: October.
Rethinking Grammatical Error Detection and Evaluation with the Amazon Mechanical Turk Joel Tetreault[Educational Testing Service] Elena Filatova[Fordham.
Predicting Text Quality for Scientific Articles Annie Louis University of Pennsylvania Advisor: Ani Nenkova.
1/7 INFO60021 Natural Language Processing Harold Somers Professor of Language Engineering.
Page 1 NAACL-HLT BEA Los Angeles, CA Annotating ESL Errors: Challenges and Rewards Alla Rozovskaya and Dan Roth University of Illinois at Urbana-Champaign.
CALL: Computer-Assisted Language Learning. 2/14 Computer-Assisted (Language) Learning “Little” programs Purpose-built learning programs (courseware) Using.
Machine Learning in Natural Language Processing Noriko Tomuro November 16, 2006.
March 1, 2009 Dr. Muhammed Al-Mulhem 1 ICS 482 Natural Language Processing INTRODUCTION Muhammed Al-Mulhem March 1, 2009.
Statistical Natural Language Processing. What is NLP?  Natural Language Processing (NLP), or Computational Linguistics, is concerned with theoretical.
SI485i : NLP Set 9 Advanced PCFGs Some slides from Chris Manning.
14: THE TEACHING OF GRAMMAR  Should grammar be taught?  When? How? Why?  Grammar teaching: Any strategies conducted in order to help learners understand,
Introduction.  Classification based on function role in classroom instruction  Placement assessment: administered at the beginning of instruction 
Lecture 1, 7/21/2005Natural Language Processing1 CS60057 Speech &Natural Language Processing Autumn 2005 Lecture 1 21 July 2005.
Na-Rae Han (University of Pittsburgh), Joel Tetreault (ETS), Soo-Hwa Lee (Chungdahm Learning, Inc.), Jin-Young Ha (Kangwon University) May , LREC.
Automated Essay Evaluation Martin Angert Rachel Drossman.
Ian Lucas Executive Director ETS Europe UK CRITERION ® Online Writing Evaluation.
Ann Shlapobersky 2013 Making Writing Their Own 1.
9/8/20151 Natural Language Processing Lecture Notes 1.
Eric Cohen Books 2007 Simply Writing - Task to Project to Bagrut What's expected and what you can do! Clarity, Expectation and Format.
The Ups and Downs of Preposition Error Detection in ESL Writing Joel Tetreault[Educational Testing Service] Martin Chodorow[Hunter College of CUNY]
Preposition Errors in ESL Writings Mohammad Moradi KOWSAR INSTITUTE.
Computational Methods to Vocalize Arabic Texts H. Safadi*, O. Al Dakkak** & N. Ghneim**
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
Lecture 12: 22/6/1435 Natural language processing Lecturer/ Kawther Abas 363CS – Artificial Intelligence.
Writing by Design to Craft a Scholarly Paper Fran Racher, RN, PhD School of Health Studies MPN Orientation September, 2011.
Automatic Detection of Tags for Political Blogs Khairun-nisa Hassanali Vasileios Hatzivassiloglou The University.
CRESST ONR/NETC Meetings, July 2003, v1 ONR Advanced Distributed Learning Linguistic Modification of Test Items Jamal Abedi University of California,
Academic Affinity and Beyond Susan DePhilippis Judith Otterburn-Martinez Atlantic Cape Community College, NJ.
Error Correction: For Dummies? Ellen Pratt, PhD. UPR Mayaguez.
October 2005CSA3180 NLP1 CSA3180 Natural Language Processing Introduction and Course Overview.
CSA2050 Introduction to Computational Linguistics Lecture 1 Overview.
What you have learned and how you can use it : Grammars and Lexicons Parts I-III.
Auckland 2012Kilgarriff: NLP and Corpus Processing1 The contribution of NLP: corpus processing.
Carolyn Penstein Rosé Language Technologies Institute Human-Computer Interaction Institute School of Computer Science With funding from the National Science.
Teaching and Learning with Technology, 4e © 2011 Pearson Education, Inc. All rights reserved. Chapter 3 Designing and Planning Technology- Enhanced Instruction.
1 An Introduction to Computational Linguistics Mohammad Bahrani.
Unit 2 The Nature of Learner Language 1. Errors and errors analysis 2. Developmental patterns 3. Variability in learner language.
Error Analysis of Two Types of Grammar for the purpose of Automatic Rule Refinement Ariadna Font Llitjós, Katharina Probst, Jaime Carbonell Language Technologies.
GCSE English Language 8700 GCSE English Literature 8702 A two year course focused on the development of skills in reading, writing and speaking and listening.
NATURAL LANGUAGE PROCESSING
Correcting Misuse of Verb Forms John Lee, Stephanie Seneff Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge ACL 2008.
Basics of Natural Language Processing Introduction to Computational Linguistics.
Twitter as a Corpus for Sentiment Analysis and Opinion Mining
The University of Illinois System in the CoNLL-2013 Shared Task Alla RozovskayaKai-Wei ChangMark SammonsDan Roth Cognitive Computation Group University.
Erasmus University Rotterdam
Automatic Fluency Assessment
Writing Analytics Clayton Clemens Vive Kumar.
Annotating ESL Errors: Challenges and Rewards
The CoNLL-2014 Shared Task on Grammatical Error Correction
Automatic Detection of Causal Relations for Question Answering
Natural Language Processing
Designing and Planning Technology-Enhanced Instruction
University of Illinois System in HOO Text Correction Shared Task
Introduction to Sentiment Analysis
Presentation transcript:

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 D’oh!

Computational Linguistics D’oh! Want computers to understand language

Computational Linguistics D’oh!   

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

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

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

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

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

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

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

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

E-rater Features Sentence fragments, garbled words Subject-Verb Agreement: the motel are … Verb form: They are need to distinguish … Pronoun Errors: Them are my reasons … Grammar Incorrect article/preposition Confused Word: affect vs. effect Faulty Comparison: It is more big Double negatives: He don’t have no candy. Usage

E-rater Features Spelling Punctuation Capitalization Missing hyphens, apostrophes Mechanics Sentence length, word repetition Passives Style Discourse sequences RST & Syntactic structures (contrast, elaboration, antithesis, etc.) Discourse

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’skas as,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.”

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

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

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.”)

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

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 in to their demands.”) “give in”  “acquiesce, surrender”

Why are prepositions hard to master? Multiple prepositions can appear in the same context: Choices to on toward onto Source Writer System Rater 1 Rater 2 “When the plant is horizontal, the force of the gravity causes the sap to move __ the underside of the stem.”

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

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

Baseball Feature Example EventWinnerLocationPrior Isotopes Win Streak Prior Capital City Win Streak Game 1IsotopesSpringfield03 Game 2Capital CitySpringfield40 Game 3Capital City 20 Game 4IsotopesSpringfield21

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

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

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

Preposition Feature Example EventPrepPrior VerbPrior NounFollowing WordPOS of Following Word Prep 1offond beerNN Prep 2atarrive theDet Prep 3with cartheDet 1.He is fond of beer. 2.The train will arrive at the Springfield Station. 3.The car with the broken wheel is in the shop.

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

Thresholds “He is fond with beer” FLAG AS ERROR

Thresholds “My sister usually gets home by 3:00” FLAG AS OK

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

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

Plugs ETS/NLP Publications: – th Workshop on Innovative Use of NLP for Educational Applications (NAACL-10) –

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

Thanks! Joel Tetreault: