Linguistics Issues in Machine Translation
β Scribed by Frank Van Eynde
- Publisher
- Bloomsbury Academic
- Year
- 1993
- Tongue
- English
- Leaves
- 258
- Series
- Linguistics: Bloomsbury Academic Collections
- Category
- Library
No coin nor oath required. For personal study only.
β¦ Synopsis
The key assumption in this text is that machine translation is not merely a mechanical process but in fact requires a high level of linguistic sophistication, as the nuances of syntax, semantics and intonation cannot always be conveyed by modern technology. The increasing dependence on artificial communication by private and corporate users makes this research area an invaluable element when teaching linguistic theory.
β¦ Table of Contents
Cover
Half-title
Title
Copyright
Contents
Preface
1. Machine translation and linguistic motivation
1. Bilingual and monolingual information
2. Four methods for reducing transfer
2.1. Word order
2.2. Articles
2.3. Lexical ambiguity
2.4. Normalisation and abstraction
3. On the (in)dispensability of transfer
3.1. A typology of bilingual operations
3.1.1. Structure preserving operations on lexical elements
3.1.2. Structure changing operations on lexical elements
3.1.3. Structure preserving operations on grammatical elements
3.1.4. Structure changing operations on grammatical elements
3.2. A hierarchy of transfer systems
4. Interlingual information and semantic universals
4.1. Three classical approaches
4.2. A new approach to interlinguality
5. Conclusions
Notes
Acknowledgements
References
2. Co-description and translation
1. The transfer model
1.1. Unification formalisms and translation
1.2. Test cases for translation
2. Projections and co-description
3. Incorporation
3.1. Argument incorporation
3.2. Modifier incorporation
3.3. Some extensions
4. Head-switching
4.1. Head-switching by r equations
4.2 Alternatives
4.3. Functional uncertainty
4.4. Conclusion
5. General conclusion
Notes
References
3. The interaction of syntax and morphology in machine translation
1. The linguistic and translational background
2. Inflection
3. Derivation
4. Compounding
5. Two issues
6. Conclusion
Notes
References
4. Dependency and machine translation
1. Two sorts of linguistic phenomena
2. Lexical selection in transfer
3. A dependency structure
4. Level of depth of dependency structures
5. A dependency grammar
6. Conditions on dependency structures
7. Some problems and difficulties in defining interface structures as dependency constructions
8. A particular proposal of dependency grammar and some application examples
9. Conclusion
References
5. On the translation of prepositions in multilingual MT
1. A methodological preliminary
2. Which prepositional phrases?
3. Two approaches to the meaning of prepositions
4. An example of semantic relations
5. The representational problem: some possible treatments
6. On the robustness of semantic relations
7. Conclusion
Notes
References
6. Translation fills the gaps: a new approach to unbounded dependencies
1. Goals and methodology
2. A characterization of unbounded dependencies
2.1 Top, middle and bottom
2.2 Trace theory and grammatical frameworks
2.3 Structural uncertainty and the subjacency condition
3. From linguistics to machine translation
3.1 Relaxed compositional translation
3.2 Compositionality and unbounded dependencies
3.3 Co-indexations in translation
4. Towards a formalization
4.1 A grammatical formalism for 'translation machines'
4.2 A sample treatment of UDCs in a fragment of English
4.3 A 'translator' notation
Acknowledgements
Notes
References
Index
π SIMILAR VOLUMES
<p>This book provides a wide variety of algorithms and models to integrate linguistic knowledge into Statistical Machine Translation (SMT). It helps advance conventional SMT to linguistically motivated SMT by enhancing the following three essential components: translation, reordering and bracketing
The field of machine translation (MT) -- the automation of translation between human languages -- has existed for more than fifty years. MT helped to usher in the field of computational linguistics and has influenced methods and applications in know
<p></p><p><span>This book is a contribution to the research community towards thinking and reflecting on what Responsible Machine Translation really means. It was conceived as an open dialogue across disciplines, from philosophy to law, with the ultimate goal of providing a wide spectrum of topics t