ACL RD-TEC 1.0 Summarization of P05-3007
Paper Title:
HIGH THROUGHPUT MODULARIZED NLP SYSTEM FOR CLINICAL TEXT
HIGH THROUGHPUT MODULARIZED NLP SYSTEM FOR CLINICAL TEXT
Authors: Serguei Pakhomov and James Buntrock and Patrick Duffy
Primarily assigned technology terms:
- algorithm
- analysis engines
- bayes classifier
- classifier
- classifiers
- computational biology
- computational linguistics
- data mining
- database
- dictionary lookup
- disambiguation
- entity identification
- entropy classifier
- finite state
- finite state transducer
- hardware
- hidden markov
- hidden markov models
- identification
- indexing
- information access
- information management
- information retrieval
- information retrieval system
- language processing
- learning
- machine learning
- maximum entropy
- maximum entropy classifier
- maximum entropy classifiers
- messaging
- mining
- modular design
- naive bayes
- naive bayes classifier
- named entity identification
- natural language processing
- nlp
- nlp system
- operating system
- parser
- pos tagger
- processing
- ranking
- retrieval system
- searching
- sentence detector annotator
- shallow parser
- statistical analysis
- statistical approaches
- tagger
- text analysis
- text processing
- text processing system
- tokenizer
- transducer
- verb phrases
- web server
Other assigned terms:
- abbreviation
- abbreviations
- ambiguous words
- annotation
- annotation process
- annotator
- annotators
- association for computational linguistics
- biology
- biomedical domain
- canonical form
- characters
- cluster
- clusters
- concept
- concepts
- design process
- dictionaries
- dictionary
- document
- document text
- entropy
- f-score
- feature
- index
- interpretation
- kappa
- kappa statistic
- key phrase
- knowledge
- lemma
- linguistic
- linguistics
- maps
- markov models
- mesh
- message
- method
- methodology
- named entities
- named entity
- natural language
- negation
- noun phrase
- noun phrases
- nouns
- part of speech
- part-ofspeech
- penn treebank
- penn treebank corpus
- phrase
- phrase level
- precision
- process
- punctuation
- queries
- query
- sentence
- sentence boundaries
- sentences
- server
- speech tag
- statistic
- structured information
- symbol
- synonym
- synonymy
- system description
- system performance
- tags
- technology
- term
- terms
- test corpus
- text
- tokens
- topics
- training
- treebank
- treebank corpus
- umls
- unstructured information
- verb
- word
- words
