ACL RD-TEC 1.0 Summarization of W99-0701
Paper Title:
UNSUPERVISED LEARNING OF WORD BOUNDARY WITH DESCRIPTION LENGTH GAIN
UNSUPERVISED LEARNING OF WORD BOUNDARY WITH DESCRIPTION LENGTH GAIN
Authors: Chunyu Kitt and Yorick Wilks
Primarily assigned technology terms:
- acquisition algorithm
- algorithm
- boundary prediction
- chunking
- complexity analysis
- expectation-maximization
- illustration
- language processing
- learner
- learning
- learning algorithm
- learning algorithms
- learning approach
- learning techniques
- lexical acquisition
- lexical acquisition algorithm
- lexical learning
- natural language processing
- nlp
- nlp system
- processing
- search
- segmentation
- terminology
- text compression
- tile
- training algorithm
- unsupervised approach
- unsupervised learning
- unsupervised learning algorithm
- viterbi
- viterbi algorithm
Other assigned terms:
- approach
- bias
- binary tree
- brown corpus
- character sequence
- characters
- chunks
- co-occurrence
- co-occurrence frequency
- corpora
- correlation
- dictionary
- english text
- experimental results
- fact
- implementation
- index
- information theory
- knowledge
- language data
- lexical item
- lexical items
- linguistic
- mdl principle
- measure
- method
- minimum description length
- n-gram
- n-grams
- names
- natural language
- natural language sentences
- precision
- proper names
- ptb
- right-hand side
- segments
- sentences
- statistical data
- tags
- technology
- terms
- text
- text corpora
- text corpus
- theory
- time complexity
- tokens
- training
- transformation
- tree
- tree structure
- utterance
- web pages
- word
- word boundaries
- word boundary
- words
- written corpora
- wsj corpus
