| Preface | p. ix |
| The Problem of Cross-Language Information Retrieval | p. 1 |
| Introduction | p. 1 |
| The Three Problems of CLIR | p. 3 |
| Finding Translations | p. 4 |
| Pruning Translation Alternatives | p. 7 |
| Weighting Translation Alternatives | p. 8 |
| Conclusion | p. 9 |
| On the Effective Use of Large Parallel Corpora in Cross-Language Text Retrieval | p. 11 |
| Introduction | p. 11 |
| Recuerdo: A Spanish Retrieval Engine | p. 13 |
| Collins Bilingual English-Spanish Dictionary | p. 14 |
| The UN Parallel Corpus | p. 14 |
| The Disambiguation Engine | p. 15 |
| Monolingual and Cross-Language Retrieval Results | p. 17 |
| The Role of Disambiguation | p. 18 |
| Further Improving Disambiguation Performance | p. 21 |
| Conclusions | p. 21 |
| Statistical Methods for Cross-Language Information Retrieval | p. 23 |
| Introduction | p. 23 |
| Previous Work | p. 24 |
| Dictionary Translation Using Expansion | p. 26 |
| Experiments | p. 27 |
| Conclusions and Future Work | p. 39 |
| Distributed Cross-Lingual Information Retrieval | p. 41 |
| The EMIR project approach | p. 42 |
| The distributed multilingual client-server architecture | p. 46 |
| Experimentation on a library catalog | p. 49 |
| Conclusion | p. 50 |
| Automatic Cross-Language Information Retrieval Using Latent Semantic Indexing | p. 51 |
| Introduction | p. 51 |
| Overview of Latent Semantic Indexing (LSI) | p. 52 |
| Cross-Language Retrieval Using LSI | p. 54 |
| Conclusion | p. 62 |
| Mapping Vocabularies Using Latent Semantics | p. 63 |
| The Problem: Managing Semantics in Medical Vocabularies | p. 64 |
| The Basis of a Solution: Latent Semantic Indexing | p. 65 |
| The Hypothesis: LSI Applied to Terms | p. 68 |
| Experiments: LSI Mappings of Medical 'Term Space' | p. 73 |
| Conclusion: Developing General, Robust Methods for Medical Semantics | p. 79 |
| Cross-Language Information Retrieval: a System for Comparable Corpus Querying | p. 81 |
| Introduction | p. 81 |
| Corpus Linguistics and Bilingual Reference Corpora | p. 82 |
| Procedures for Comparable Corpus Processing | p. 84 |
| First Results | p. 88 |
| Application to Cross Language Information Retrieval | p. 90 |
| A Language Conversion Front-End for Cross-Language Information Retrieval | p. 93 |
| Introduction | p. 93 |
| Problems in Translation Equivalent Selection | p. 94 |
| Description of the Method | p. 96 |
| Implementation | p. 101 |
| Experimental Results | p. 102 |
| Discussion | p. 103 |
| Conclusion | p. 104 |
| The Systran Nlp Browser: an Application of Machine Translation Technology in Cross-Language Information Retrieval | p. 105 |
| Introduction | p. 105 |
| Systran Nlp Browser | p. 107 |
| Discussion | p. 115 |
| Conclusion | p. 117 |
| A Weighted Boolean Model for Cross-Language Text Retrieval | p. 119 |
| Introduction | p. 119 |
| Boolean vs. Vector Space Retrieval | p. 120 |
| Background: Extended Boolean Models | p. 123 |
| A New Weighted Boolean Model | p. 125 |
| Background: Cross-Language Text Retrieval | p. 127 |
| Testing the Weighted Boolean Model | p. 130 |
| Commentary | p. 135 |
| Building a Large Multilingual Test Collection From Comparable News Documents | p. 137 |
| Introduction | p. 137 |
| Evaluation using Seed Documents | p. 140 |
| The ETH Multilingual Test Collection | p. 142 |
| Summary and Conclusions | p. 149 |
| Evaluating Cross-Language Text Filtering Effectiveness | p. 151 |
| Introduction | p. 151 |
| Adaptive Multilingual Text Filtering | p. 152 |
| Ideal Experiment Design | p. 154 |
| Use of Available Corpora | p. 156 |
| Results | p. 158 |
| Conclusions | p. 160 |
| References | p. 163 |
| Index | p. 177 |
| Table of Contents provided by Syndetics. All Rights Reserved. |