ACL RD-TEC 1.0 Summarization of W02-0301
Paper Title:
TUNING SUPPORT VECTOR MACHINES FOR BIOMEDICAL NAMED ENTITY RECOGNITION
TUNING SUPPORT VECTOR MACHINES FOR BIOMEDICAL NAMED ENTITY RECOGNITION
Authors: Jun'ichi Kazama and Takaki Makino and Yoshihiro Ohta and Jun'ichi Tsujii
Primarily assigned technology terms:
- algorithm
- binary classifier
- biomedical information extraction
- biomedical named entity recognition
- c + +
- caching
- chunking
- class splitting
- classification
- classifier
- classifiers
- computational linguistics
- database
- english pos tagger
- entity recognition
- entity recognition system
- feature combination
- feature representation
- feature selection
- feature truncation
- hidden markov
- hidden markov model
- identification
- information extraction
- inner product
- java
- java programming language
- kernel
- kernels
- language processing
- learning
- learning approach
- learning method
- learning methods
- learning techniques
- machine learning
- machine learning approach
- machine learning techniques
- markov model
- maximum entropy
- maximum entropy method
- maximum entropy system
- named entity recognition
- natural language processing
- nlp
- noise reduction
- normalization
- optimization
- pairwise classification
- parallel training
- parallelization
- part-of-speech tagging
- phrase chunking
- polynomial kernel
- pos tagger
- processing
- programming language
- recognition
- recognition system
- splitting
- support vector machines
- svm classifier
- svm learning
- svm-based recognition
- svm-based system
- tagger
- tagging
- tagging method
- tokenizer
- transcription
- truncation
- tuning
- unsupervised learning
- unsupervised learning method
- viterbi
- viterbi algorithm
Other assigned terms:
- annotated corpora
- annotated corpus
- annotation
- approach
- association for computational linguistics
- biomedical domain
- biomedical information
- cache
- case
- character type
- class distribution
- corpora
- data sparseness
- data sparseness problem
- determiners
- disjunction
- distribution
- entity class
- entity recognition task
- entropy
- experimental results
- f-score
- feature
- feature description
- feature set
- feature sets
- feature space
- genia
- genia corpus
- hmm state feature
- identification task
- implementation
- interpretation
- kernel evaluation
- kernel function
- knowledge
- large corpus
- linguistic
- linguistics
- mapping
- measures
- medline
- method
- n-gram
- named entities
- named entity
- named entity task
- natural language
- ne task
- nlp tasks
- noise
- noun phrases
- nouns
- optimization problem
- parallelism
- part-of-speech
- part-of-speech information
- part-of-speech tag
- part-of-speech tags
- penn treebank
- phrase
- pos information
- precision
- probability
- process
- query
- recognition accuracy
- recognition task
- representations
- research topic
- semantic
- semantic class
- sentence
- sentences
- sparseness problem
- state feature
- statistics
- substring
- support vector
- svms
- tag set
- tagging model
- tags
- technique
- text
- training
- training data
- training samples
- training time
- treebank
- unbalanced class distribution
- vocabulary
- word
- word features
- words
