ACL RD-TEC 1.0 Summarization of J00-2004
Paper Title:
MODELS OF TRANSLATIONAL EQUIVALENCE AMONG WORDS
MODELS OF TRANSLATIONAL EQUIVALENCE AMONG WORDS
Primarily assigned technology terms:
- algorithm
- annotation tool
- approximation
- bilingual concordancer
- classification
- co-occurrence counting
- computational linguistics
- computer system
- computing
- concept representation
- cross-language information retrieval
- cutoff
- decomposition
- decomposition method
- direct association
- em algorithm
- estimation algorithm
- estimation method
- estimation process
- expectation-maximization
- fitting procedure
- good-turing smoothing
- greedy algorithm
- greedy approximation
- heuristic search
- hidden markov
- hidden markov model
- hill-climbing
- information retrieval
- learning
- learning algorithms
- learning techniques
- likelihood approach
- likelihood estimation
- link assignment
- linking
- machine learning
- machine learning techniques
- machine translation
- machine translation systems
- markov model
- matching
- maximum likelihood
- maximum likelihood approach
- maximum likelihood estimation
- maximum matching
- measuring
- mechanical translation
- model estimation
- model reestimation
- modeling
- parameter estimation
- part-of-speech tagger
- phrasal translation
- probabilistic translation
- probability function
- quantitative evaluation
- query translation
- reestimation
- search
- searching
- single-word translation
- smoothing
- smoothing method
- standardization
- statistical machine translation
- statistical method
- statistical translation
- table lookup
- tagger
- term translation
- translation model estimation
- translation model reestimation
- translation modeling
- translation process
- translation systems
- unsupervised learning
- word alignment
- word-to-word translation
Other assigned terms:
- adjective
- aligned sentence
- ambiguous word
- annotation
- annotators
- approach
- association for computational linguistics
- association score
- bias
- bilingual dictionaries
- bilingual dictionary
- binomial distribution
- bitext
- bitext map
- bitext space
- canonical form
- case
- characters
- co-occurrence
- co-occurrence count
- co-occurrence frequency
- co-occurrence information
- co-occurrences
- coefficient
- collocate
- collocation
- compounds
- computational complexity
- concept
- concepts
- conceptual structures
- concordance
- conditional probabilities
- conditional probability
- content words
- contingency table
- convergence
- corpora
- corpus size
- correlation
- data sets
- dictionaries
- dictionary
- distribution
- document
- english corpus
- entropy
- estimation
- evaluation method
- evaluation metrics
- evaluations
- feature
- french
- french translation
- french word
- function words
- generation
- generation process
- genre
- gold standard
- gold standard test
- grammars
- heuristic
- human judgments
- human translation
- hypotheses
- hypothesis
- independence assumption
- information science
- information sources
- interannotator agreement
- interpretation
- joint distribution
- joint probability
- joint probability distribution
- knowledge
- language model
- language pair
- language pairs
- lexical conceptual structures
- lexicographer
- lexicography
- lexicon
- lexicon entries
- lexicon entry
- likelihood
- linguistic
- linguistics
- local maxima
- mathematics
- meaning
- measure
- method
- model parameters
- model performance
- natural languages
- noise
- noise model
- pairs of words
- parallel texts
- parameter space
- part of speech
- part-of-speech
- parts of speech
- perplexity
- phrase
- phrase structure
- possible translation
- precision
- predictive power
- probabilities
- probability
- probability distribution
- probability distributions
- procedure
- process
- pronouns
- punctuation
- query
- random sample
- relation
- representations
- right-hand side
- running time
- segments
- sentence
- sentences
- similarity function
- similarity metric
- source language
- sparse data
- sparse data problem
- statistic
- statistical models
- statistical significance
- statistical translation model
- stem
- style
- sun microsystems
- symbols
- synsets
- taxonomy
- term
- terms
- test data
- test set
- text
- text corpora
- text segment
- text segments
- tokens
- training
- training corpus
- training data
- translation lexicon
- translation model
- translation models
- translation probabilities
- translation probability
- translation task
- translational equivalence
- translations
- tree
- tree adjoining grammars
- trees
- unigram
- verb
- vocabulary
- word
- word classes
- word frequencies
- word order
- word sense
- word sequence
- word sequences
- word type
- word types
- word-to-word translation model
- wordnet
- wordnet synsets
- words
