Correcting Misuse of Verb Forms

25
Correcting Misuse of Verb Forms John Lee , Stephanie Seneff Computer Science and Arti cial Intelligence Laboratory, MIT, Cambridge ACL 2008

description

Correcting Misuse of Verb Forms. John Lee , Stephanie Seneff Computer Science and Artificial Intelligence Laboratory,  MIT, Cambridge. ACL 2008. Outline. Introduction Background System Baselines Data Evaluation Conclusions. Introduction. Introduction. - PowerPoint PPT Presentation

Transcript of Correcting Misuse of Verb Forms

Page 1: Correcting Misuse                     of Verb Forms

Correcting Misuse of Verb Forms

John Lee , Stephanie SeneffComputer Science and Artificial Intelligence Laboratory,

 MIT, Cambridge

ACL 2008

Page 2: Correcting Misuse                     of Verb Forms

Outline

Introduction Background System Baselines Data Evaluation Conclusions

Page 3: Correcting Misuse                     of Verb Forms

Introduction

Page 4: Correcting Misuse                     of Verb Forms

Introduction

Page 5: Correcting Misuse                     of Verb Forms

Introduction

Page 6: Correcting Misuse                     of Verb Forms

Outline

Introduction Background System Baselines Data Evaluation Conclusions

Page 7: Correcting Misuse                     of Verb Forms

Background

The goal is to correct confusions among the five forms, as well as the infinitive caused by semantic and syntactic errors.

Semantic Errors

Suppose one wants to say “I am prepared for the exam”, but writes “I am preparing for the exam”.

Page 8: Correcting Misuse                     of Verb Forms

Background

Syntactic Errors

Subject-Verb AgreementHe *have been living there since June.

Auxiliary AgreementHe has been *live there since June.

ComplementationHe wants *live there.

Page 9: Correcting Misuse                     of Verb Forms

Outline

Introduction Background System Baselines Data Evaluation Conclusions

Page 10: Correcting Misuse                     of Verb Forms

System

Step1Automatic Parsing

“My father is *work in the laboratory.”

Page 11: Correcting Misuse                     of Verb Forms

System

Step2Replacing the verb forms

Page 12: Correcting Misuse                     of Verb Forms

System

Page 13: Correcting Misuse                     of Verb Forms

System

Step3N-gram counts as a filterUsing WEB 1T N-GRAM corpus. Prepared by Google Inc.

Page 14: Correcting Misuse                     of Verb Forms

Outline

Introduction Background System Baselines Data Evaluation Conclusions

Page 15: Correcting Misuse                     of Verb Forms

Baselines

majority baselineNo correction.

verb-only baseline(Only used in Auxiliary Agreement & Complementation)

It attempts corrections only when the word in question is actually tagged as a verb.

Page 16: Correcting Misuse                     of Verb Forms

Outline

Introduction Background System Baselines Data Evaluation Conclusions

Page 17: Correcting Misuse                     of Verb Forms

Data

Development DataAQUAINT Corpus (English News Text)

Evaluation DataJLE (Japanese Learners of English corpus)For 167 of the transcribed interviews, totalling 15,637 sentences.Test Set477 sentences (3.1%) contain subject-verb agreement errors, and 238 (1.5%) contain auxiliary agreement and complementation errors

Page 18: Correcting Misuse                     of Verb Forms

Data

Evaluation DataHKUST (Hong Kong University of Science and Technology)It contains a total of 2556 sentences.

Page 19: Correcting Misuse                     of Verb Forms

DataEvaluation MetricAccuracy(true neg + true pos) / total number of sentencesRecalltrue pos / (true pos + false neg + inv pos)Detection Precision(true pos + inv pos) / (true pos + inv pos + false pos)Correction Precisiontrue pos / (true pos + false pos + inv pos)

Page 20: Correcting Misuse                     of Verb Forms

Outline

Introduction Background System Baselines Data Evaluation Conclusions

Page 21: Correcting Misuse                     of Verb Forms

Evaluation

JLEResults for Subject-Verb Agreement

Corpus Method Accuracy Precision(correction)

Precision(detection)

Recall

JLE allmajority

98.93%96.95%

81.61% 83.93% 80.92%

Results for Auxiliary Agreement & Complementation

Corpus Method Accuracy Precision(correction)

Precision(detection)

Recall

JLE allverb-onlymajority

98.94%98.85%98.47%

68.00%71.43%

80.67%84.75%

42.86%31.51%

Page 22: Correcting Misuse                     of Verb Forms

Evaluation

HKUSTResults for Auxiliary Agreement & ComplementationTwo native speakers of English were given the edited sentences, as well as the original input.For each pair, they were asked to select one of four statements: one of the two is better, or both are equally correct, or both are equally incorrect.

Corpus Method Accuracy Precision(correction)

Precision(detection)

Recall

HKUST all Not available 71.71% not available not available

Kappa: 0.76

Page 23: Correcting Misuse                     of Verb Forms

Evaluation

Page 24: Correcting Misuse                     of Verb Forms

Outline

Introduction Background System Baselines Data Evaluation Conclusions

Page 25: Correcting Misuse                     of Verb Forms

Conclusions

This paper proposes a method to correct English verb form

errors made by non-native speakers. Investigation of the ways the ways in which verb form errors

affect parse trees.