ACL RD-TEC 1.0 Summarization of P06-2117
Paper Title:
BOOSTING STATISTICAL WORD ALIGNMENT USING LABELED AND UNLABELED DATA
BOOSTING STATISTICAL WORD ALIGNMENT USING LABELED AND UNLABELED DATA
Authors: Hua Wu and Haifeng Wang and Zhanyi Liu
Primarily assigned technology terms:
- adaboost
- algorithm
- boosting
- boosting algorithm
- classification
- clustering
- computational linguistics
- disambiguation
- em algorithm
- em training
- entity classification
- error rate reduction
- estimation method
- expectation maximization
- giza
- learner
- learning
- learning algorithm
- linear interpolation
- machine translation
- machine translation system
- named entity classification
- nlp
- parameter estimation
- parsing
- rate reduction
- semi-supervised algorithm
- semi-supervised learning
- sense disambiguation
- statistical machine translation
- statistical word alignment
- supervised learning
- supervised method
- translation system
- unsupervised method
- word aligner
- word alignment
- word sense disambiguation
Other assigned terms:
- alignment error rate
- alignment model
- alignment models
- approach
- association for computational linguistics
- bilingual corpora
- case
- chinese word
- confidence measure
- corpora
- data sparseness
- data sparseness problem
- distortion probability
- distribution
- error rate
- estimation
- evaluation metrics
- experimental results
- f-measure
- fact
- ibm model
- ibm models
- index
- interpolation
- linguistics
- measure
- method
- named entity
- nlp tasks
- precision
- probabilities
- probability
- sentence
- sentence pair
- sentences
- source language
- source sentence
- sparseness problem
- statistics
- supervised model
- target sentence
- target word
- testing set
- toolkit
- training
- training data
- translation accuracy
- translation probability
- word
- word alignment links
- word alignment model
- word classes
- word sense
- words
