ACL RD-TEC 1.0 Summarization of W93-0301
Paper Title:
ROBUST BILINGUAL WORD ALIGNMENT FOR MACHINE AIDED TRANSLATION
ROBUST BILINGUAL WORD ALIGNMENT FOR MACHINE AIDED TRANSLATION
Authors: Ido Dagan and Kenneth Church and Willian Gale
Primarily assigned technology terms:
- algorithm
- alignment algorithm
- alignment method
- bilingual terminology
- bilingual word alignment
- character recognition
- character-based alignment
- computing
- dynamic programming
- dynamic programming algorithm
- dynamic programming approach
- em algorithm
- indexing
- information retrieval
- iterative process
- latent semantic indexing
- linear extrapolation
- linear interpolation
- machine translation
- machine translation systems
- maximum likelihood
- monitoring
- optical character recognition
- parameter estimation
- programming algorithm
- random sampling
- recognition
- relative distance
- rough alignment
- sampling
- search
- semantic indexing
- sentence alignment
- sentence-based alignment
- statistical machine translation
- stratified sampling
- svd analysis
- terminology
- translation service
- translation systems
- translator
- translators
- weighting
- word alignment
- word alignment algorithm
Other assigned terms:
- aligning corpora
- alignment error rate
- approach
- bilingual lexicons
- case
- concept
- concordance
- content words
- corpora
- device
- dialog
- distribution
- document
- electronic form
- english corpus
- english sentence
- english translation
- english vocabulary
- error rate
- estimation
- fact
- french
- french corpus
- french sentence
- french text
- french word
- function words
- heuristics
- hypothesis
- interpolation
- latent semantic
- likelihood
- likelihood probability
- machine translation project
- mapping
- maps
- method
- noise
- normal distribution
- paragraphs
- parallel text
- parallel texts
- probabilities
- probability
- probability estimates
- process
- programming approach
- queries
- query
- relative frequency
- semantic
- sentence
- sentence boundaries
- sentence level
- sentences
- source language
- source text
- standard deviation
- stratified sample
- target language
- target text
- term
- terms
- text
- thesaurus
- tokens
- training
- training data
- training set
- translation probabilities
- translation probability
- translations
- vocabulary
- window size
- word
- word frequencies
- word order
- words
