ACL RD-TEC 1.0 Summarization of I05-3023
Paper Title:
PERCEPTRON LEARNING FOR CHINESE WORD SEGMENTATION
PERCEPTRON LEARNING FOR CHINESE WORD SEGMENTATION
Authors: Yaoyong Li and Chuanjiang Miao and Kalina Bontcheva and Hamish Cunningham
Primarily assigned technology terms:
- algorithm
- binary classification
- character-based classification
- chinese word segmentation
- classification
- classifier
- classifiers
- collapsing
- cross validation
- cross-validation
- document classification
- encoding
- entity recognition
- information extraction
- kernel
- language processing
- learning
- learning algorithm
- linear kernel
- machine learning
- margin algorithm
- named entity recognition
- natural language processing
- nlp
- perceptron
- perceptron algorithm
- perceptron learning
- preprocessing
- processing
- recognition
- segmentation
- support vector machines
- thresholding
- validation
- word segmentation
Other assigned terms:
- binary classification problem
- blank space
- characters
- chinese word
- classification problem
- co-occurrence
- co-occurrences
- context window
- corpora
- document
- english text
- f-measure
- fact
- feature
- feature vector
- generalisation
- implementation
- knowledge
- large training
- method
- methodology
- named entity
- natural language
- nlp tasks
- open test
- positive and negative examples
- probability
- quadratic kernel
- segmentation problem
- segments
- sentence
- sentences
- support vector
- symbol
- test data
- test set
- text
- trained model
- training
- training and test data
- training corpus
- training data
- training example
- training examples
- training set
- word
- words