ACL RD-TEC 1.0 Summarization of P06-1119
Paper Title:
LEVERAGING REUSABILITY: COST-EFFECTIVE LEXICAL ACQUISITION FOR LARGE-SCALE ONTOLOGY TRANSLATION
LEVERAGING REUSABILITY: COST-EFFECTIVE LEXICAL ACQUISITION FOR LARGE-SCALE ONTOLOGY TRANSLATION
Authors: G. Craig Murray and Bonnie J. Dorr and Jimmy Lin and Jan Hajič and Pavel Pecina
Primarily assigned technology terms:
- algorithm
- alignment process
- bilingual alignment
- bilingual term extraction
- computational linguistics
- cross-language information retrieval
- databases
- decomposition
- indexing
- information access
- information retrieval
- information systems
- knowledgeacquisition
- lexical acquisition
- longest matching
- machine translation
- machine translation systems
- matching
- measuring
- morphology
- objective evaluation
- off-the-shelf machine translation
- phrase translation
- prioritization
- recursive calculation
- sampling
- searching
- stratified sampling
- subjective evaluation
- term extraction
- terminology
- translation process
- translation system
- translation systems
- translators
- word translation
Other assigned terms:
- aligned corpus
- approach
- association for computational linguistics
- automated translation
- baseline score
- bias
- bilingual dictionaries
- bilingual dictionary
- bilingual term
- bleu
- bleu score
- bleu scores
- case
- comparable corpora
- concept
- concepts
- controlled vocabulary
- corpora
- czech-english dependency treebank
- data set
- data sparsity
- dependency treebank
- dictionaries
- dictionary
- distribution
- evaluations
- fact
- heuristic
- heuristic rules
- high-quality translation
- human translation
- index
- keyword
- keyword phrase
- knowledge
- leaf
- lexical information
- lexical resources
- lexicon
- linguistics
- machine translation quality
- manual translation
- meaning
- meanings
- measures
- medical terminology
- mesh
- method
- multilingual information
- ontologies
- ontology
- ordered list
- parallel corpora
- parallel corpus
- phrase
- probabilities
- probability
- process
- process model
- random sample
- reference translations
- reordering
- segments
- spoken language
- stem
- substring
- system performance
- target language
- technique
- technologies
- term
- terms
- test data
- text
- thesaurus
- tokens
- translation accuracy
- translation dictionary
- translation lexicon
- translation output
- translation probability
- translation quality
- translations
- treebank
- video content
- vocabulary
- word
- word choice
- word order
- words