ACL RD-TEC 1.0 Summarization of W03-0806
Paper Title:
BLUEPRINT FOR A HIGH PERFORMANCE NLP INFRASTRUCTURE
BLUEPRINT FOR A HIGH PERFORMANCE NLP INFRASTRUCTURE
Primarily assigned technology terms:
- active learning
- annotation representation
- beam search
- beam-search
- binding
- c + +
- chunker
- chunking
- classification
- co-training
- coding
- compiler
- databases
- decision trees
- dialogue systems
- english pos tagger
- entity classification
- feature extraction
- finite state
- finite state machines
- gaussian smoothing
- generative programming
- graphical user interface
- interfaces
- internet
- iterative estimation
- java
- java native interface
- language processing
- learning
- learning methods
- machine learning
- machine learning methods
- matching
- maximum entropy
- maximum entropy model
- memory-based learning
- message passing
- modelling
- named entity classification
- native interface
- natural language processing
- nlp
- nlp systems
- nlp technology
- nltk
- open source software
- operating system
- optimisation
- pos tagger
- pos tagging
- processing
- prolog
- querying
- reading
- recogniser
- recognition
- search
- sequence tagging
- sequential tagging
- smoothing
- software engineering
- speech recognition
- standardisation
- statistical modelling
- string matching
- support vector machines
- tagger
- taggers
- tagging
- text classification
- text engineering
- text processing
- tokenization
- transduction
- transformation-based learning
- user interface
- user interfaces
- web service
- weka
Other assigned terms:
- annotated corpora
- annotation
- approach
- array
- bayes model
- beam
- chunk
- classification task
- cluster
- composition
- corpora
- development cycle
- disk
- document
- document format
- entropy
- entropy models
- estimation
- feature
- feature sets
- gazetteer
- implementation
- inheritance
- interpreter
- large corpora
- lexical item
- lexicon
- manual annotation
- maximum entropy models
- message
- method
- named entity
- names
- natural language
- ontology
- procedure
- process
- processing time
- programming approach
- programming paradigm
- query
- representations
- scripting language
- sentence
- sentence boundary
- statistical models
- subtrees
- support vector
- tagging task
- tags
- teaching
- technology
- text
- text classification task
- toolkit
- training
- transformation
- trees
- user
- web pages
- word
- words
- wrapper
