One of the hardest problems for automatic translation is generating
words and inflections that are obligatory in the target language, but
not in the source language. This work is the first to provide a fully
implemented solution to the problem of generating determiners
and determining number. Using a semantic representation and a
series of three heuristic algorithms, this solution provides the most
probable context-sensitive translation. It gives insight into natural
language processing in general, and machine translation, semantic
analysis, and generation from underspecified inputs in particular.
This book finishes with an extensive evaluation of the implemented
algorithms.
Francis Bond is a research scientist at NTT Communication Science Laboratories at the Nippon Telegraph and Telephone Corporation.
Errata
- Table of Contents i
- Preface iii
- List of Figures v
- List of Tables vi
- Notational Conventions and Symbols ix
- 1 Introduction 1
- 2 Background 9
- 2.1 Syntax 10
- 2.2 Reference (NP) 14
- 2.3 Countability and Number 22
- 2.4 Determiners and (In)Definiteness 35
- 2.5 Thematic Marking in Japanese 52
- 2.6 Determiners and Number in Machine Translation 59
- 3 Semantic Representation 79
- 3.1 Noun Phrases in English 80
- 3.2 Noun Phrases in Japanese 89
- 3.3 Types of Reference 98
- 3.4 Boundedness, Countability and Number 98
- 3.5 Definiteness and Topicalization 110
- 4 Automatic Interpretation 113
- 4.1 The Algorithm for Determining NP Referentiality 114
- 4.2 The Algorithm for Determining NP Countability andNumber 124
- 4.3 The Algorithm for Generating Determiners for Referential NPs 128
- 4.4 Summary of the Three Algorithms 135
- 4.5 Translation of Generic Noun Phrases 137
- 4.6 The Actual Generation of Articles 139
- 5 Evaluation and Discussion 143
- 5.1 Results and Evaluation 144
- 5.2 Discussion 156
- 6 Conclusion 161
- Appendix A: A Description of ALT-J/E 163
- A.1 System Architecture 163
- A.2 Semantic Ontology and Dictionaries 165
- A.3 English Structure 172
- Appendix B: Lexical Information 175
- B.1 Overview 175
- B.2 Lexical Information for Nouns 176
- B.3 Information (for Modifiers) 184
- B.4 English Morphological Dictionary 186
- B.5 Adjective Ordering 186
- Appendix C: Sample of Output 189
- Bibliography 191
- Index 205
3/15/2005