Handbook of Natural Language Processing and Machine Translation


Handbook of Natural Language Processing and Machine Translation (2011) Joseph P. Olive etc eds


Contents

1 Data Acquisition and Linguistic Resources … 1

1.1 Introduction … 1

1.2 Data Collection, Distribution, and Management … 2

1.3 Human Annotation … 14

1.4 Automatic Annotation … 64

2 Machine Translation from Text … 133

2.1 Introduction … 133

2.2 Segmentation, Tokenization and Preprocessing … 135

2.3 Word Alignment … 164

2.4 Translation Models … 183

2.5 Language Modeling for SMT … 252

2.6 Search and Complexity … 271

2.7 Adaptation and Data Selection … 297

2.8 System Combination … 324

3.1 Introduction … 399

3.2 Front End Features … 401

3.3 Improved Speech Acoustic Models … 428

3.4 Language Models … 460

3.5 Language-Specific Models and Systems: Mandarin … 485

3.6 Language-Specific Models and Systems: Arabic… 520

3.7 Integration of Speech Recognition and Translation … 569

4 Distillation … 617

4.1 Introduction … 617

4.2 Template-Based Query Development … 618

4.3 Architecture and Implementation of a Distillation System … 623

4.4 Enabling Technology Breakthroughs to Improve Distillation Capabilities … 636

4.5 Distillation in an Integrated GALE system … 690

4.6 Evaluating Distillation Technology … 716

5 Machine Translation Evaluation and Optimization … 745

5.1 Introduction … 745

5.2 Automatic and Semi-Automatic Measures … 758

5.3 Tasks and Human-in-the-Loop Measures … 768

5.4 GALE Machine Translation Metrology: Definition, Implementation, and Calculation … 783

5.5 Use of Evaluation for Optimization … 812

5.6 Searching for Better Automatic MT Metrics … 818

6 Operational Engines … 845

6.1 Introduction … 845

6.2 Implementation of Operational Engines … 846

6.3 Evaluation of Operational Engines … 905

Concluding Remarks … 933