ACL RD-TEC 1.0 Summarization of P06-2037
Paper Title:
LOW-COST ENRICHMENT OF SPANISH WORDNET WITH AUTOMATICALLY TRANSLATED GLOSSES: COMBINING GENERAL AND SPECIALIZED MODELS
LOW-COST ENRICHMENT OF SPANISH WORDNET WITH AUTOMATICALLY TRANSLATED GLOSSES: COMBINING GENERAL AND SPECIALIZED MODELS
Authors: Jesús Giménez and Lluís Màrquez
Primarily assigned technology terms:
- algorithm
- approximate search
- beam search
- boosting
- bootstrap
- bootstrap resampling
- decoder
- disambiguation
- dynamic programming
- error analysis
- giza
- illustration
- language modeling
- linear interpolation
- machine translation
- machine translation system
- matching
- modeling
- mt system
- optimization
- phrase extraction
- phrase-based statistical machine translation
- phrase-based translation
- question answering
- question answering systems
- resampling
- rule-based system
- search
- sense disambiguation
- smoothing
- smt system
- sri language modeling
- statistical machine translation
- statistical machine translation system
- syntactic transfer
- system construction
- text matching
- translation system
- translator
- tuning
- viterbi
- word sense disambiguation
Other assigned terms:
- beam
- bleu
- bleu score
- candidate translation
- case
- catalan
- commercial system
- communication theory
- concept
- corpora
- data sets
- development set
- dictionaries
- dictionary
- dictionary definitions
- europarl corpus
- evaluation metrics
- external knowledge
- f-measure
- fact
- grammaticality
- gtm f-measure
- heuristic
- implementation
- interpolation
- knowledge
- language model
- language modeling toolkit
- language models
- lexical level
- measure
- method
- modeling toolkit
- monolingual corpora
- mt evaluation
- n-gram
- nist
- noisy channel
- nouns
- out-of-domain corpus
- parallel corpora
- parallel corpus
- parallel text
- parallel texts
- phrase
- precision
- probabilities
- probability
- process
- relation
- relative frequency
- semantic
- semantic relation
- sentence
- sentence level
- sentences
- signal
- size of the corpus
- statistical models
- synonymy
- synset
- synsets
- system performance
- tagged corpora
- technique
- technology
- test set
- text
- theory
- tokens
- toolkit
- topology
- training
- training corpus
- training data
- training set
- transfer rules
- translation candidates
- translation model
- translation models
- translation probability
- trigram
- word
- word alignments
- word sense
- wordnet
- words
