中国学生英语作文自动评分模型的构建PDF|Epub|txt|kindle电子书版本网盘下载

中国学生英语作文自动评分模型的构建PDF格式电子书版下载

注意：本站所有压缩包均有解压码： 点击下载压缩包解压工具

Part One Introduction1

Introducing the Study2

0.1 Introductory remarks2

0.2 Need for this study3

0.2.1 Theoretical considerations3

0.2.2 Practical considerations7

0.3 Description of the study10

0.4 Organization of the study11

0.5 Summary12

Part Two Literature Review13

Chapter 1 A Review of Existing Computer-Assisted Essay Scoring Systems14

1.1 Introduction14

1.2 Key concepts14

1.2.1 Computer-assisted essay scoring14

1.2.2 EFL writing assessment16

1.3 Existing computer-assisted essay scoring systems17

1.3.1 Project Essay Grade(PEG):A form-focused system17

1.3.2 Intelligent Essay Assessor(IEA):A content-focused system20

1.3.3 E-rater:A hybrid system with a modular structure22

1.3.4 An appraisal of the three existing systems25

1.4 Lessons from existing essay scoring systems28

1.5 Summary31

Chapter 2 Studies on Measures of Writing Quality33

2.1 Introduction33

2.2 Measures of writing quality in the literature33

2.2.1 Measures of the quality of language34

2.2.2 Measures of the quality of content and organization51

2.3 An overview of the measures in the literature57

2.4 A conceptual model for the computer-assisted scoring of EFL essays61

2.5 Proposed measures of EFL writing quality65

2.5.1 Proposed measures of the quality of language in EFL writing65

2.5.2 Proposed measures of the quality of content in EFL writing69

2.5.3 Proposed measures of the quality of organization in EFL writing71

2.6 Summary75

Part Three Methodology77

Chapter 3 Research Questions and Data Preparation78

3.1 Introduction78

3.2 Research questions78

3.3 The corpus80

3.4 The rating scheme82

3.4.1 Selecting a rating scale82

3.4.2 The revised rating scale84

3.4.3 The evaluation of content87

3.4.4 The weighting scheme90

3.5 Rating91

3.5.1 Rater selection92

3.5.2 Rater training92

3.5.3 The rating sessions93

3.6 Score reliability94

3.7 Summary96

Chapter 4 Text Analysis and Statistical Analysis97

4.1 Introduction97

4.2 Tools97

4.3 Essay feature extraction99

4.3.1 Language features100

4.3.2 Content features103

4.3.3 Organizational features110

4.4 Data analysis111

4.4.1 Correlation analysis111

4.4.2 Multiple regression analysis112

4.4.3 Stages of data analysis113

4.5 Summary117

Part Four Results and Discussion119

Chapter 5 Identifying Predictors of EFL Writing Quality120

5.1 Introduction120

5.2 Linguistic features and writing quality120

5.2.1 Fluency and writing quality123

5.2.2 Complexity of language and writing quality126

5.2.3 Measures of linguistic idiomaticity and appropriateness138

5.3 Results of content analysis144

5.3.1 Results of Latent Semantic Analysis145

5.3.2 Procedural vocabulary and essay score149

5.4 Essay organization and writing quality151

5.4.1 Paragraphing and writing quality152

5.4.2 Discourse conjuncts and writing quality159

5.4.3 Demonstratives,pronouns,connective and writing quality159

5.5 Power of the predictors proposed in this study159

5.6 Summary161

Chapter 6 A Statistical Model for Computer-Assisted Essay Scoring164

6.1 Introduction164

6.2 Diagnosing the preliminary model165

6.3 The refined model168

6.4 Predictors and aspects of writing quality measured172

6.4.1 Predictors in the language module173

6.4.2 Predictors in the content module178

6.4.3 Predictors in the organization module181

6.4.4 Interdependence of the modules183

6.5 Implementing the model185

6.6 Summary187

Chapter 7 Validating the Model188

7.1 Introduction188

7.2 Cross-validating the model188

7.3 Reliability of computer scores in cross-validation191

7.3.1 Aspects of reliability191

7.3.2 Consistency estimates193

7.3.3 Consensus estimates195

7.4 Double cross-validation198

7.4.1 Constructing the model198

7.4.2 Model statistics and estimated equation199

7.5 Reliability of computer scores in double cross-validation201

7.6 Comparison with existing essay scoring systems204

7.6.1 Comparison with PEG205

7.6.2 Comparison with IEA208

7.6.3 Comparison with E-rater212

7.7 Summary214

Part Five Conclusion215

Chapter 8 Conclusion216

8.1 Major findings216

8.1.1 A model for the computer-assisted scoring of EFL essays216

8.1.2 Predictors of EFL writing quality220

8.2 Limitations of the study223

8.2 Future work224

References226

Appendices249

Appendix Ⅰ PEG's proxes and their beta values(Page 1968)249

Appendix Ⅱ Page's(1995)model and variables251

Appendix Ⅲ Argument weight253

Appendix Ⅳ Examples of good openings and endings255

Appendix Ⅴ Scoring table(Organization ＆ Content)256

Appendix Ⅵ Scoring table(Language)257

Appendix Ⅶ List of stopwords258

Appendix Ⅷ Lemma list(excerpt)262

Appendix Ⅸ List of content words266

Appendix Ⅹ Sample essays283

Appendix Ⅺ POS-tagged samples286

Chapter1

Table 1.1 Comparison of strengths and weaknesses of existing essay scoring systems26

Table 1.2 Approaches and measured constructs28

Chapter2

Table 2.1 Measures of writing quality in previous studies58

Chapter3

Table 3.1 Comparison of holistic and analytic scales(from Weigle 2002)83

Table 3.2 Jacobs et al.'s(1981)scale:Aspects of quality and their emphasis85

Table 3.3 Modified scheme:Aspects of writing quality86

Table 3.4 Aspects of writing quality and their emphasis in the revised scale91

Table 3.5 Inter-rater correlations(Training set)95

Table 3.6 Mean and standard deviation of scores (Training set)95

Table 3.7 Inter-rater correlations(Validation set)95

Table 3.8 Mean and standard deviation of scores(Validation set)95

Chapter4

Table 4.1 Directly extracted language features100

Table 4.2 Computed language features100

Chapter5

Table 5.1 Measures of the quality of language explored122

Table 5.2 Correlations between fluency measures and essay scores123

Table 5.3 Correlations between general lexical features and essay scores127

Table 5.4 Correlations between TTR,Index of Guiraud and essay scores130

Table 5.5 Correlations between the number of words in VFP lists and essay scores131

Table 5.6 Correlation between uncommon-common word ratio and essay scores134

Table 5.7 Correlations between measures of syntactic complexity and essay scores135

Table 5.8 Examples of recurrent word combinations140

Table 5.9 Correlation between the number of RWCs and essay scores140

Table 5.10 Correlations between the use of prepositions,the use of the definite article and essay scores143

Table 5.11 Correlations between standard SVD measures,revised SVD measures and essay scores146

Table 5.12 Correlation between the number of PV items and essay scores149

Table 5.13 Correlation between paragraphing and essay scores154

Table 5.14 Categories of discourse conjuncts156

Table 5.15 Correlation between discourse conjuncts and essay scores157

Table 5.16 Power of the predictors proposed in this study160

Table 5.17 Variables and aspects of writing quality they measure161

Chapter6

Table 6.1 Summary for the preliminary model165

Table 6.2 Problematic variables in the model167

Table 6.3 Predicting power of the model168

Table 6.4 Predictors and their beta weights170

Table 6.5 Predictors in the language module173

Table 6.6 Predicting power of the language module176

Table 6.7 Coefficients of predictors in the language module177

Table 6.8 Predictors in the content module178

Table 6.9 Predicting power of the content module180

Table 6.10 Coefficients of predictors in the content module180

Table 6.11 Predictors in the organization module181

Table 6.12 Predicting power of the organization module182

Table 6.13 Coefficients of predictors in the organization module183

Table 6.14 The unique power of the content module183

Table 6.15 The unique power of the organization module184

Table 6.16 The unique power of the language module185

Chapter7

Table 7.1 Pearson correlations between human raters and the computer194

Table 7.2 Cronbach's alpha coefficients195

Table 7.3 Exact agreement between human raters and computer196

Table 7.4 Exact-plus-adjacent agreement between human raters and computer197

Table 7.5 A summary of reliability estimates198

Table 7.6 Model summary(double cross-validation)199

Table 7.7 Regression coefficients(double cross-validation)200

Table 7.8 Consistency coefficients of reliability(double cross-validation)202

Table 7.9 Consensus estimates of reliability(double cross-validation)203

Table 7.10 Pearson correlations and exact-plus-adjacent agreement205

Table 7.11 Reliability of PEG's first experiment(from Page 2003)205

Table 7.12 Reliability of PEG's NAEP experiment(Page 1994)206

Table 7.13 Reliability of PEG's Praxis experiment(from Page 2003)207

Table 7.14 Major experiments with PEG207

Table 7.15 Representative experiments with LSA210

Table 7.16 E-rater's mean agreement with human raters(Burstein et al. 1998a)212

Table 7.17 E-rater's reliability reported in Burstein et al.(2001)213

Chapter8

Table 8.1 A list of reconfirmed predictors221

Table 8.2 Revised predictors and their correlations with essay quality222

Chapter1

Figure 1.1 Modularity in the computer-assisted essay scoring model30

Chapter2

Figure 2.1 Relationship between the No. of types and the No. of tokens in a text44

Figure 2.2 A conceptual model for the computer-assisted scoring of EFL essays62

Chapter4

Figure 4.1 Term-by-document matrix105

Figure 4.2 Weighted term-by-document matrix106

Figure 4.3 Singular Value Decomposition(SVD)107

Figure 4.4 Matrix reconstruction107

Figure 4.5 Reconstructed matrix108

Figure 4.6 The reference in the revised approach of LSA109

Figure 4.7 Flow chart of the model-training stage113

Figure 4.8 Flow chart of the cross-validation phase114

Figure 4.9 Flow chart of the double cross-validation phase116

Chapter5

Figure 5.1 Relationship between the number of paragraphs and essay scores152

Chapter6

Figure 6.1 Relationship between the standardized predicted value and the dependent variable169

Figure 6.2 Estimated Equation 1172

Figure 6.3 Implementing the model187

Chapter7

Figure 7.1 Computing essay scores190

Figure 7.2 Variables and computer-generated scores191

Figure 7.3 Estimated equation 2(double cross-validation)201