ACL RD-TEC 1.0 Summarization of P02-1061
Paper Title:
TEACHING A WEAKER CLASSIFIER: NAMED ENTITY RECOGNITION ON UPPER CASE TEXT
TEACHING A WEAKER CLASSIFIER: NAMED ENTITY RECOGNITION ON UPPER CASE TEXT
Authors: Hai Leong Chieu and Hwee Tou Ng
Primarily assigned technology terms:
- adaboost
- algorithm
- broadcasting
- character recognition
- classification
- classifier
- classifiers
- co-training
- cutoff
- dynamic programming
- dynamic programming algorithm
- em algorithm
- entity classification
- entity recognition
- entity recognizer
- entropy classifier
- example selection
- feature selection
- feature split
- generalized iterative scaling
- internet
- iterative method
- iterative scaling
- language processing
- learning
- learning methods
- machine learning
- machine learning methods
- machinelearning
- maximum entropy
- maximum entropy classifier
- maximum entropy framework
- maximumlikelihood
- message understanding
- named entity classification
- named entity recognition
- named entity recognizer
- natural language processing
- normalization
- optical character recognition
- orthographic representation
- page classification
- parser
- part-of-speech tagging
- processing
- programming algorithm
- recognition
- recognizer
- reporting
- self-training
- speech recognition
- tagging
- text retrieval
- unsupervised learning
- web page classification
Other assigned terms:
- acronym
- annotation
- annotation effort
- approach
- binary features
- case
- case information
- classification task
- concept
- corpora
- dictionaries
- distribution
- document
- english language
- entropy
- estimation
- experimental results
- f-measure
- feature
- independence assumption
- lexicon
- linguistics
- meaning
- measure
- message
- message understanding conferences
- method
- name class
- named entities
- named entity
- named entity task
- names
- natural language
- noise
- part-of-speech
- person names
- precision
- probabilities
- probability
- probability distribution
- procedure
- process
- sentence
- substring
- suffixes
- system description
- tags
- teaching
- test data
- text
- tokens
- training
- training and test data
- training data
- training material
- transition probability
- understanding
- unlabeled text
- web page
- word
- word classes
- wordnet
- words
