ACL RD-TEC 1.0 Summarization of N06-2029
Paper Title:
EXPLOITING VARIANT CORPORA FOR MACHINE TRANSLATION
EXPLOITING VARIANT CORPORA FOR MACHINE TRANSLATION
Authors: Michael Paul and Eiichiro Sumita
Primarily assigned technology terms:
Other assigned terms:
- aligned sentence
- ambiguity
- approach
- bleu
- bleu score
- bleu scores
- cluster
- corpora
- data sets
- english corpus
- error rate
- evaluation measures
- geometric mean
- hypotheses
- hypothesis
- iwslt evaluation
- japanese sentences
- kanji
- knowledge
- large corpora
- linguistic
- linguistic phenomena
- linguistic structure
- meaning
- measure
- measures
- method
- multiple variant corpora
- n-gram
- nouns
- oracle
- orthography
- parallel text
- parallel text corpora
- precision
- pronouns
- reference translations
- sentence
- sentences
- source language
- statistical model
- statistical models
- statistical significance
- system performance
- test set
- text
- text corpora
- text corpus
- training
- training corpora
- training corpus
- training data
- translation hypothesis
- translation knowledge
- translation model
- translation models
- translation output
- translation quality
- translation task
- translations
- vocabulary
- vocabulary size
- word
- word error rate
- word type
- words
