ACL RD-TEC 1.0 Summarization of W00-1314
Paper Title:
WORD ALIGNMENT OF ENGLISH-CHINESE BILINGUAL CORPUS BASED ON CHUCKS
WORD ALIGNMENT OF ENGLISH-CHINESE BILINGUAL CORPUS BASED ON CHUCKS
Authors: Le Sun and Youbing Jin and Lin Du and Yufang Sun
Primarily assigned technology terms:
- algorithm
- alignment algorithm
- boundary prediction
- chinese segmentation
- chinese word segmentation
- chunk alignment
- chunker
- chunking
- em algorithm
- example-based machine translation
- floppy disk drive
- information retrieval
- information retrieval system
- machine translation
- machine translation system
- matching
- multilingual information retrieval
- networking
- nlp
- parser
- parsing
- retrieval system
- segmentation
- shallow parsing
- statistical machine translation
- statistical method
- string matching
- terminology
- text alignment
- translation system
- word alignment
- word segmentation
Other assigned terms:
- alignment problem
- approach
- bilingual corpora
- bilingual corpus
- bilingual dictionary
- bilingual lexicon
- chinese language
- chinese sentence
- chinese text
- chinese translation
- chinese word
- chinese words
- chunk
- chunk tag
- chunks
- co-occurrence
- co-occurrence frequency
- community
- contemporary english
- corpora
- dictionaries
- dictionary
- disk
- distortion probability
- english corpus
- english language
- english sentence
- english-chinese corpus
- experimental results
- grammars
- heuristic
- knowledge
- knowledge base
- labeling
- large corpus
- lexicography
- lexicon
- linguistic
- linguistic knowledge
- measure
- method
- multilingual information
- multilingual terminology
- nlp applications
- nlp community
- noise
- paragraph
- parse
- parse tree
- phrase
- phrase level
- pos tag
- preposition
- probabilities
- probability
- procedure
- process
- relation
- semantic
- semantic class
- semantic classes
- sense similarity
- sentence
- sentence level
- sentence pair
- sentence structure
- sentences
- statistical model
- synonymy
- syntactic structure
- syntax
- system architecture
- tagged corpus
- terms
- text
- training
- training corpus
- training data
- translation model
- translation models
- translation probability
- translations
- tree
- word
- word candidate
- word level
- word level alignment
- word order
- word pair
- words
