ACL RD-TEC 1.0 Summarization of H90-1069
Paper Title:
TOWARDS UNDERSTANDING TEXT WITH A VERY LARGE VOCABULARY
TOWARDS UNDERSTANDING TEXT WITH A VERY LARGE VOCABULARY
Authors: Damaris Ayuso and R. Bobrow and Dawn MacLaughlin and Marie Meteer and Lance Ramshaw and Rich Schwartz and Ralph Weischedel
Primarily assigned technology terms:
- capitalization
- database
- hypothesizing
- information processing
- information system
- interfaces
- iterative procedure
- language interfaces
- language processing
- language understanding
- learning
- maximum-likelihood
- modeling
- modelling
- morphology
- natural language processing
- natural language systems
- natural language understanding
- nlp
- nlp system
- nlp systems
- parser
- part of speech tagging
- probabilistic modeling
- processing
- question-answering
- random selection
- ranking
- search
- speech processing
- speech systems
- speech tagging
- speech technology
- spoken language systems
- subcategorization
- supervised training
- tagging
- unification
- unsupervised training
- verb subcategorization
Other assigned terms:
- ambiguity
- annotation
- approach
- case
- common facts database
- conditional probabilities
- conditional probability
- context-free grammars
- context-free rule
- corpora
- dictionaries
- dictionary
- dictionary definitions
- disambiguating word
- distribution
- error rate
- fact
- feature
- formalism
- frame
- grammar
- grammars
- hand-crafted knowledge
- heuristics
- histogram
- input string
- intention
- interpretation
- knowledge
- language model
- large corpora
- lexical features
- lexical information
- lexicon
- likelihood
- method
- natural language
- noun phrases
- parse
- part of speech
- partial parses
- parts of speech
- phrase
- precision
- predictive power
- prepositional phrase
- probabilistic language model
- probabilistic model
- probabilistic models
- probabilities
- probability
- probability distribution
- probability estimates
- probability model
- procedure
- process
- punctuation
- punctuation mark
- relation
- right-hand side
- scalability
- search space
- semantic
- semantic class
- semantic classes
- semantic constraints
- semantic features
- semantic information
- semantic relation
- semantic representation
- sentence
- sentences
- size of the corpus
- spoken language
- subcategorization frame
- subcategorization frames
- subcategorization information
- supervised mode
- syntactic and semantic information
- syntactic structure
- syntax
- syntax and semantics
- system performance
- tag sequence
- tagged corpus
- tags
- technology
- terms
- test set
- text
- training
- training data
- training set
- tree
- treebank
- treebank corpus
- trees
- understanding
- unification formalism
- uniform probability
- verb
- verb arguments
- verb sense
- vocabulary
- word
- word sense
- word senses
- word sequence
- words
