ACL RD-TEC 1.0 Summarization of W93-0311
Paper Title:
CORPUS-BASED ADAPTATION MECHANISMS FOR CHINESE HOMOPHONE DISAMBIGUATION
CORPUS-BASED ADAPTATION MECHANISMS FOR CHINESE HOMOPHONE DISAMBIGUATION
Primarily assigned technology terms:
- adaptive learning
- algorithm
- automatic evaluation
- character recognition
- chinese homophone disambiguation
- chinese language modeling
- classification
- coding
- corpus-based adaptation
- databases
- decoding
- dictionary lookup
- disambiguation
- disambiguation problem
- dynamic programming
- extraction procedure
- frequency counting
- homophone disambiguation
- language modeling
- learning
- learning methods
- learning procedure
- lexicon-based word hypothesizer
- linguistic decoding
- machine translation
- modeling
- nlp
- part-of-speech tagging
- path finding
- phonetic decoding
- recognition
- recognition system
- recognition systems
- search
- search algorithm
- searching
- segmentation
- speech recognition
- speech recognition system
- speech recognition systems
- spelling
- spelling checker
- tagging
- text classification
- tile
- viterbi
- viterbi algorithm
- viterbi search
- viterbi search algorithm
- weighting
- word learning
- word segmentation
- word-lattice search
Other assigned terms:
- approach
- bidirectional model
- bigram
- case
- characters
- checker
- chinese characters
- chinese corpora
- chinese homophone
- chinese language
- chinese word
- compound words
- compounds
- concept
- concepts
- constraint satisfaction
- corpora
- dictionary
- experimental results
- hypotheses
- implementation
- input text
- language models
- lattice
- lexical entries
- lexicography
- lexicon
- linguistic
- lookahead
- mandarin chinese
- markov models
- mechanisms
- method
- n-gram
- n-grams
- names
- news corpus
- nlp applications
- part-of-speech
- parts-of-speech
- personal names
- pinyin
- procedure
- process
- projection
- pronunciation
- proper name
- proper names
- punctuation
- semantic
- semantic categories
- sentence
- statistics
- syllables
- symbols
- technology
- testing set
- text
- text corpora
- text corpus
- training
- training set
- user
- word
- word frequencies
- word frequency
- word lattice
- words