ACL RD-TEC 1.0 Summarization of W98-1103
Paper Title:
USING A PROBABILISTIC TRANSLATION MODEL FOR CROSS-LANGUAGE INFORMATION RETRIEVAL
USING A PROBABILISTIC TRANSLATION MODEL FOR CROSS-LANGUAGE INFORMATION RETRIEVAL
Authors: Jian-Yun Nie and Pierre Isabelle and George Foster
Primarily assigned technology terms:
- algorithm
- automatic translation
- bilingual terminology
- cross-language information retrieval
- cross-language ir
- database
- databases
- dictionary lookup
- document indexing
- document search
- expectation maximization
- expectation maximization algorithm
- indexing
- information retrieval
- ir system
- machine translation
- machine translation systems
- matching
- maximization algorithm
- measuring
- monolingual ir system
- morphological analysis
- mt system
- mt systems
- preprocessing
- probabilistic translation
- processing
- query expansion
- query translation
- retrieval process
- retrieving
- scoring
- search
- search process
- selection process
- spoken translation
- terminology
- text processing
- text retrieval
- translation method
- translation systems
- translator
- translators
- transtype
- vector space model
- weighting
Other assigned terms:
- ambiguity
- ambiguous word
- approach
- bilingual dictionaries
- bilingual dictionary
- bilingual parallel corpus
- canonical form
- case
- citation
- co-occurrence
- conditional probability
- content words
- corpora
- dictionaries
- dictionary
- dictionary entry
- distribution
- document
- document frequency
- document vector
- domain-specific information
- english query
- english sentence
- evaluations
- fact
- feature
- french
- french corpus
- french sentence
- french translation
- french word
- grammar
- hansard corpus
- index
- index terms
- inverse document frequency
- knowledge
- language model
- lexical translation
- likelihood
- mapping
- maps
- meaning
- meanings
- measure
- measures
- mechanisms
- method
- names
- natural language
- natural language query
- natural languages
- nist
- noise
- nouns
- parallel corpora
- parallel corpus
- parallel texts
- precision
- priori
- probabilistic model
- probabilities
- probability
- probability distribution
- process
- proper names
- punctuation
- queries
- query
- query vector
- relative frequency
- retrieval performance
- schema
- sentence
- sentences
- silence
- source language
- source language sentence
- source language word
- sources of information
- specialized terminology
- statistics
- stem
- stems
- symbols
- synonyms
- synonymy
- syntactic structure
- syntax
- system performance
- target language
- target language sentence
- technical terminology
- technology
- term
- term frequency
- terms
- test corpus
- text
- topics
- training
- training corpus
- translation knowledge
- translation model
- translation models
- translation probabilities
- translation probability
- translational equivalence
- translations
- tree
- vector space
- verb
- vocabulary
- word
- word lists
- word meaning
- word pair
- word stem
- words
