ACL RD-TEC 1.0 Summarization of C96-1037
Paper Title:
ALIGNING MORE WORDS WITH HIGH PRECISION FOR SMALL BILINGUAL CORPORA
ALIGNING MORE WORDS WITH HIGH PRECISION FOR SMALL BILINGUAL CORPORA
Authors: Sur-Jin Ker and Jason J. S. Chang
Primarily assigned technology terms:
- algorithm
- alignment algorithm
- alignment process
- alignment system
- bilingual lexicography
- classification
- computational linguistics
- dictionary lookup
- disambiguation
- dynamic programming
- em algorithm
- greedy algorithm
- identification
- information retrieval
- knowledge engineering
- learner
- learning
- machine translation
- morphological analysis
- nlp
- part-of-speech tagging
- preprocessing
- processing
- rough alignment
- rule acquisition
- sense disambiguation
- sense tagging
- sentence alignment
- statistical machine translation
- structural disambiguation
- tagging
- tagging system
- terminology
- terminology extraction
- tile
- translation process
- word alignment
- word alignment algorithm
- word sense disambiguation
- word-alignment
- word-based approach
- word-by-word translation
- word-sense disambiguation
Other assigned terms:
- ambiguity
- anchor
- approach
- bilingual corpora
- bilingual corpus
- bilingual dictionaries
- bilingual dictionary
- case
- characters
- class-based approach
- contemporary english
- corpora
- dictionaries
- dictionary
- distortion probability
- document
- dynamic programming procedure
- english sentence
- estimation
- experimental results
- implementation
- kanji
- knowledge
- language model
- language pairs
- lexical information
- lexical knowledge
- lexical resources
- lexical translation
- lexicography
- lexicon
- likelihood
- linguistic
- linguistic filter
- linguistics
- method
- mutual information
- nlp tasks
- paragraph
- part-of-speech
- phrase
- pp attachment
- precision
- probabilities
- probability
- procedure
- process
- query
- sense ambiguity
- sense definition
- sense distinction
- sense information
- sentence
- sentences
- size of the corpus
- source sentence
- source text
- statistic
- statistical approach
- statistics
- synonyms
- syntactical structure
- tagged corpus
- target sentence
- target text
- target word
- technical document
- testing data
- text
- text segment
- thesaurus
- training
- training data
- translation model
- translation probabilities
- translation probability
- translations
- word
- word model
- word pair
- word sense
- word sense ambiguity
- words
