ACL RD-TEC 1.0 Summarization of J03-3004
Paper Title:
WEBMT: DEVELOPING AND VALIDATING AN EXAMPLE-BASED MACHINE TRANSLATION SYSTEM USING THE WORLD WIDE WEB
WEBMT: DEVELOPING AND VALIDATING AN EXAMPLE-BASED MACHINE TRANSLATION SYSTEM USING THE WORLD WIDE WEB
Authors: Andy Way and Nano Gough
Primarily assigned technology terms:
- algorithm
- alignment method
- alignment process
- approximation
- automatic evaluation
- batch processing
- case marking
- case-marking
- chunk combination
- computational linguistics
- computing
- data-oriented parsing
- database
- databases
- dynamic programming
- ebmt system
- example-based machine translation
- fuzzy matching
- grammar optimization
- graphical interface
- hybrid method
- induction
- levenshtein
- linking
- machine translation
- machine translation system
- mapping function
- marker-based alignment
- matching
- measuring
- mt system
- mt systems
- n-gram segmentation
- n-gram-based segmentation
- n-gram-based segmentation method
- optimization
- parsing
- phrasal lexicon
- phrasal translation
- processing
- ranking
- retrieving
- scoring
- search
- search process
- searching
- segmentation
- segmentation method
- segmentation process
- shallow processing
- statistical approaches
- statistical word alignment
- translation memory
- translation process
- translation system
- translator
- translators
- validation
- validation process
- verb phrases
- web-based machine translation
- weighting
- word alignment
- word alignment tool
- word insertion
- word linking
- world wide web
Other assigned terms:
- adjective
- alignment procedure
- annotators
- approach
- bigram
- bilingual corpus
- bilingual dictionary
- bilingual lexicon
- bitext
- bleu
- boundary friction
- case
- characters
- chunk
- chunks
- co-occurrence
- concepts
- conditional probabilities
- context-free grammars
- corpora
- data sets
- derivations
- determiner
- determiners
- dictionary
- distribution
- document
- english verb
- error rate
- evaluation measures
- evaluation methodology
- evaluation metrics
- exact match
- fact
- finite verb
- french
- french language
- grammar
- grammars
- head noun
- html document
- human translation
- hypothesis
- input string
- intelligibility
- knowledge
- language pair
- language pairs
- levenshtein distance
- lexemes
- lexical item
- lexical items
- lexical resources
- lexicon
- likelihood
- linguistic
- linguistic resources
- linguistics
- main verb
- mapping
- mappings
- measure
- measures
- method
- methodology
- morphemes
- morphological variant
- n-gram
- n-grams
- natural languages
- noise
- nonterminal
- noun phrases
- oracle
- ordered list
- parallel corpus
- penn treebank
- penn-ii treebank
- phrase
- plural noun
- precision
- prepositional phrases
- prepositions
- probabilities
- probability
- procedure
- process
- pronoun
- pronouns
- query
- random order
- relation
- right-hand side
- seed
- segments
- sentence
- sentences
- signal
- similarity metrics
- source language
- string similarity
- subject-verb agreement
- sublanguage
- subtrees
- surface form
- symbol
- symbols
- syntactic structure
- system performance
- tags
- target language
- target string
- technical terms
- term
- terms
- test data
- test set
- text
- tm system
- tokens
- training
- training corpus
- transitive verb
- translation candidate
- translation candidates
- translation knowledge
- translation lexicon
- translation pair
- translation pairs
- translation quality
- translations
- treebank
- user
- verb
- verb forms
- web page
- word
- word alignments
- word error rate
- word level
- word order
- words
