ACL RD-TEC 1.0 Summarization of W05-0826
Paper Title:
COMBINING LINGUISTIC DATA VIEWS FOR PHRASE-BASED SMT
COMBINING LINGUISTIC DATA VIEWS FOR PHRASE-BASED SMT
Authors: Jesús Giménez and Lluís Màrquez
Primarily assigned technology terms:
- data representation
- database
- decoder
- decoding
- giza
- global phrase extraction
- linear interpolation
- local phrase extraction
- machine translation
- parameter estimation
- parsing
- phrase extraction
- phrase-based translation
- pos-tagging
- pre-processing
- scoring
- shallow parsing
- smoothing
- statistical machine translation
- statistical parameter estimation
- tokenization
- translation process
- tuning
- viterbi
- word-based translation
Other assigned terms:
- all content words
- annotation
- approach
- bitext
- bleu
- bleu score
- case
- chunk
- chunks
- concept
- data sets
- data sparsity
- development set
- estimation
- evaluation metrics
- experimental results
- heuristic
- implementation
- interpolation
- knowledge
- language model
- lemma
- lexical-semantic database
- linguistic
- linguistic annotation
- linguistic data
- linguistic information
- meanings
- method
- named entities
- nist
- parallel texts
- phrase
- phrase-based translation model
- possible translation
- process
- relative frequency
- sbar
- semantic
- semantic roles
- syntax
- system description
- target word
- technology
- text
- tokens
- training
- training data
- translation model
- translation models
- translation pair
- verb
- word
- word sense
- word senses
- word-based translation model
- wordnet
- words
