ACL RD-TEC 1.0 Summarization of W03-1309
Paper Title:
PROTEIN NAME TAGGING FOR BIOMEDICAL ANNOTATION IN TEXT
PROTEIN NAME TAGGING FOR BIOMEDICAL ANNOTATION IN TEXT
Authors: Kaoru Yamamoto and Taku Kudo and Akihiko Konagaya and Yuji Matsumoto
Primarily assigned technology terms:
- analyzer
- approximate matching
- approximate string matching
- approximation
- basenp recognition
- brill tagger
- chunking
- classification
- coding
- deep analysis
- dependency parser
- dictionary lookup
- dynamic programming
- feature extraction
- illustration
- information extraction
- kernel
- language processing
- learning
- learning approaches
- logical analysis
- machine learning
- machine learning approaches
- matching
- morphological analysis
- morphological analyzer
- name recognition
- name tagging
- parser
- parsing
- part-of-speech tagging
- preprocessing
- processing
- protein name recognition
- protein name tagging
- protein tagger
- recognition
- recognizer
- rule-based approach
- search
- searching
- segmentation
- sequential classification
- string matching
- svm approach
- svm-based chunking
- tagger
- tagging
- tagging method
- tokenization
- transcription
- transformation-based learning
- voting
- weighted voting
- word segmentation
- word-based segmentation
Other assigned terms:
- ambiguity
- annotated corpus
- annotation
- approach
- basenp
- binary feature
- binary features
- biomedical annotation
- biomedical domain
- boundary ambiguity
- case
- characters
- chunk
- chunk tag
- compound words
- compounds
- context window
- data structure
- dictionary
- experimental results
- f-score
- fact
- feature
- feature vectors
- gene names
- gene ontology
- genia
- genia corpus
- indicator morpheme
- intention
- joint probability
- kappa
- lexeme
- lexemes
- lexical features
- lexicon
- local context
- measures
- medline
- method
- morpheme
- morphemes
- name class
- names
- noun phrase
- noun phrases
- ontology
- part-of-speech
- parts of speech
- phrase
- precision
- probability
- process
- protein information
- protein information resource
- protein names
- punctuation
- punctuation marks
- root category
- sentence
- specialist lexicon
- statistical significance
- substring
- suffix
- symbol
- synonyms
- syntactic feature
- syntactic features
- tag sequence
- tags
- tagset
- technique
- technologies
- terms
- text
- thesaurus
- tokens
- training
- training data
- training dataset
- trigram
- umls
- umls specialist lexicon
- window size
- word
- word dependency
- word sequence
- words
- yapex corpus
