ACL RD-TEC 1.0 Summarization of W06-2402
Paper Title:
GROUPING MULTI-WORD EXPRESSIONS ACCORDING TO PART-OF-SPEECH IN STATISTICAL MACHINE TRANSLATION
GROUPING MULTI-WORD EXPRESSIONS ACCORDING TO PART-OF-SPEECH IN STATISTICAL MACHINE TRANSLATION
Authors: Patrik Lambert and Rafael Banchs
Primarily assigned technology terms:
- algorithm
- alignment evaluation
- analysis tool
- automatic generation
- automatic translation
- beam-search
- bmwe extraction
- decoder
- dynamic programming
- error analysis
- extraction technique
- grouping
- identification
- identification process
- language modelling
- machine translation
- matching
- modelling
- parallel training
- phrase translation
- phrase-based translation
- phrase-based translation approach
- pos-tagging
- search
- search engine
- segmentation
- smt system
- statistical alignment
- statistical machine translation
- statistical technique
- tagger
- translation evaluation
- translation system
- viterbi
- word alignment
- word translation
- word-to-word alignment
Other assigned terms:
- aligned corpus
- alignment error rate
- alignment model
- alignment models
- approach
- beam-search strategy
- bilingual phrase
- bilingual sentence
- bleu
- bleu score
- case
- corpora
- data sets
- data sparseness
- determiners
- dictionaries
- dictionary
- dictionary entries
- distribution
- edit distance
- error rate
- evaluation measures
- evaluations
- experimental results
- extraction process
- fact
- feature
- generation
- hypotheses
- hypothesis
- idiomatic expressions
- inflected forms
- inflection
- joint probability
- language model
- large corpus
- lexical model
- literal translation
- log-linear combination
- meaning
- measures
- method
- modality
- multi-word expression
- mwes
- n-gram
- n-gram model
- n-grams
- noise
- noisy channel
- nouns
- parallel corpora
- parallel training corpus
- part-of-speech
- particles
- phrase
- phrase-based translation model
- precision
- probabilities
- probability
- probability distribution
- procedure
- process
- reference translations
- relative frequency
- sentence
- sentence pair
- sentences
- size of the corpus
- source language
- statistics
- tag set
- target language
- target language model
- target languages
- target sentence
- technique
- terms
- test corpus
- test data
- tokens
- toolkit
- training
- training and test data
- training corpus
- training data
- transcriptions
- translation accuracy
- translation direction
- translation hypothesis
- translation model
- translation probability
- translation quality
- translations
- verb
- verb group
- vocabulary
- vocabulary size
- word
- word error rate
- word sequences
- wordnet
- words
