|
" Machine translation "
Pushpak Bhattacharyya.
| Document Type
|
:
|
BL
|
| Record Number
|
:
|
751618
|
| Doc. No
|
:
|
b571577
|
| Main Entry
|
:
|
Pushpak Bhattacharyya.
|
| Title & Author
|
:
|
Machine translation\ Pushpak Bhattacharyya.
|
| Publication Statement
|
:
|
Boca Raton : CRC Press, Taylor & Francis Group, 2015
|
| Page. NO
|
:
|
xxiv, 234 pages : illustrations ; 25 cm
|
| ISBN
|
:
|
1439897182
|
|
|
:
|
: 9781439897188
|
| Contents
|
:
|
List of FiguresList of TablesPrefaceAcknowledgmentsAbout the AuthorIntroductionA Feel for a Modern Approach to Machine Translation: Data-Driven MTMT Approaches: Vauquois TriangleUnderstanding Transfer over the Vauquois TriangleUnderstanding Ascending and Descending TransferLanguage Divergence with Illustration between Hindi and EnglishSyntactic DivergenceLexical-Semantic DivergenceThree Major Paradigms of Machine TranslationMT EvaluationAdequacy and FluencyAutomatic Evaluation of MT OutputSummaryFurther ReadingLearning Bilingual Word MappingsA Combinatorial ArgumentNecessary and Sufficient Conditions for Deterministic Alignment in Case of One-to-One Word MappingA Naive Estimate for Corpora RequirementDeeper Look at One-to-One AlignmentDrawing Parallels with Part of Speech TaggingHeuristics-Based Computation of the VE x VF TableIterative (EM-Based) Computation of the VE x VF TableInitialization and Iteration 1 of EMIteration 2Iteration 3Mathematics of AlignmentA Few Illustrative Problems to Clarify Application of EMDerivation of Alignment ProbabilitiesExpressing the E- and M-Steps in Count FormComplexity ConsiderationsStorageTimeEM: Study of Progress in Parameter ValuesNecessity of at Least Two SentencesOne-Same-Rest-Changed SituationOne-Changed-Rest-Same SituationSummaryFurther ReadingIBM Model of AlignmentFactors Influencing P(f|e)Alignment Factor aLength Factor mIBM Model 1The Problem of Summation over Product in IBM Model 1EM for Computing P(f|e)Alignment in a New Input Sentence PairTranslating a New Sentence in IBM Model 1: DecodingIBM Model 2EM for Computing P(f|e) in IBM Model 2Justification for and Linguistic Viability of P(i|j,l,m)IBM Model 3SummaryFurther ReadingPhrase-Based Machine TranslationNeed for Phrase AlignmentCase of Promotional/Demotional DivergenceCase of Multiword (Includes Idioms)Phrases Are Not Necessarily Linguistic PhrasesAn Example to Illustrate Phrase Alignment TechniqueTwo-Way AlignmentsSymmetrizationExpansion of Aligned Words to PhrasesPhrase TableMathematics of Phrase-Based SMTUnderstanding Phrase-Based Translation through an ExampleDeriving Translation Model and Calculating Translation and Distortion ProbabilitiesGiving Different Weights to Model ParametersFixing Values: TuningDecodingExample to Illustrate DecodingMosesInstalling MosesWorkflow for Building a Phrase-Based SMT SystemPreprocessing for MosesTraining Language ModelTraining Phrase ModelTuningDecoding Test DataEvaluation MetricMore on MosesSummaryFurther ReadingRule-Based Machine Translation (RBMT)Two Kinds of RBMT: Interlingua and TransferWhat Exactly Is Interlingua?Illustration of Different Levels of TransferUniversal Networking Language (UNL)Illustration of UNLUNL Expressions as Binary PredicatesWhy UNL?Interlingua and Word KnowledgeHow Universal Are UWs?UWs and MultilingualityUWs and MultiwordsUW Dictionary and WordnetComparing and Contrasting UW Dictionary and WordnetTranslation Using InterlinguaIllustration of Analysis and GenerationDetails of English-to-UNL Conversion: With IllustrationIllustrated UNL GenerationUNL-to-Hindi Conversion: With IllustrationFunction Word InsertionCase Identification and Morphology GenerationRepresentative Rules for Function Words InsertionSyntax PlanningTransfer-Based MTWhat Exactly Are Transfer Rules?Case Study of Marathi-Hindi Transfer-Based MTKrudant: The Crux of the Matter in M-H MTM-H MT SystemSummaryFurther ReadingExample-Based Machine TranslationIllustration of Essential Steps of EBMTDeeper Look at EBMT's WorkingWord MatchingMatching of HaveEBMT and Case-Based ReasoningText Similarity ComputationWord Based SimilarityTree and Graph Based SimilarityCBR's Similarity Computation Adapted to EBMTRecombination: Adaptation on Retrieved ExamplesBased on Sentence PartsBased on Properties of Sentence PartsRecombination Using Parts of Semantic GraphEBMT and Translation MemoryEBMT and SMTSummaryFurther ReadingIndex
|
| Abstract
|
:
|
The proposed project on machine translation will be based on the above pedagogy, through the study of phenomena, formalization, and then elucidation of the techniques. Case studies, examples, and historical perspectives will be used extensively to cover the material. The primary aim of this book is to provide an accessible text book on machine translation covering lucidly the foundations, insights, and case studies for practical concerns. The book would also point towards where the field is currently and heading towards in the future--This book discusses the three major paradigms of machine translation: rule-based, statistical, and example-based, and provides examples and insight-generating exercises.'--
|
| Subject
|
:
|
BUSINESS ECONOMICS -- Statistics.
|
| Subject
|
:
|
Machine translating.
|
| Subject
|
:
|
Translating and interpreting -- Data processing.
|
| LC Classification
|
:
|
P308.P874 2015
|
| Added Entry
|
:
|
Pushpak Bhattacharyya
|
| |