ACL RD-TEC 1.0 Summarization of W06-1660
Paper Title:
EMPIRICAL STUDY ON THE PERFORMANCE STABILITY OF NAMED ENTITY RECOGNITION MODEL ACROSS DOMAINS
EMPIRICAL STUDY ON THE PERFORMANCE STABILITY OF NAMED ENTITY RECOGNITION MODEL ACROSS DOMAINS
Authors: Hong Lei Guo and Li Zhang and Zhong Su
Primarily assigned technology terms:
- active learning
- algorithm
- automatic content extraction
- classification
- classification method
- classifier
- computational linguistics
- corresponding training
- cross-validation
- data selection
- decoding
- dynamic programming
- english ner
- entity recognition
- entity recognition system
- information extraction
- information integration
- informative sample selection
- language processing
- learning
- learning algorithms
- learning approach
- learning approaches
- learning method
- learning methods
- machine learning
- machine learning algorithms
- machine learning approach
- machine learning approaches
- machine translation
- named entity recognition
- natural language processing
- optimization
- performance enhancement
- processing
- recognition
- recognition system
- risk minimization
- robust risk minimization
- sample selection
- segmentation
- selection method
- sequential classification
- supervised learning
- tagging
- text classification
- training algorithm
- training method
- training sample selection
- truncation
- word segmentation
Other assigned terms:
- annotated corpus
- annotation
- approach
- association for computational linguistics
- baseline performance
- characters
- chinese characters
- chinese word
- chinese words
- classification problem
- conditional probability
- conditional probability model
- confidence score
- confidence scores
- corpus size
- data set
- data sets
- distribution
- document
- domain information
- evaluations
- events
- experimental results
- f-measure
- feature
- feature vector
- fmeasure
- language model
- language processing applications
- linguistic
- linguistic features
- linguistics
- maps
- measure
- method
- named entities
- named entity
- names
- natural language
- natural language processing applications
- ner model
- optimization problem
- part of speech
- precision
- probability
- probability model
- process
- recognition model
- semantic
- semantic features
- semantic information
- sentence
- sentences
- set size
- standard deviation
- statistic
- statistical data
- statistics
- suffixes
- tags
- test data
- test data set
- text
- tokens
- training
- training and test data
- training data
- training data set
- training samples
- training set
- weight vector
- word
- words
