ACL RD-TEC 1.0 Summarization of W04-2802
Paper Title:
TOWARDS MEASURING SCALABILITY IN NATURAL LANGUAGE UNDERSTANDING TASKS
TOWARDS MEASURING SCALABILITY IN NATURAL LANGUAGE UNDERSTANDING TASKS
Authors: Robert Porzel and Rainer Malaka
Primarily assigned technology terms:
- algorithm
- automatic speech recognition
- classification
- classification method
- computing
- dialogue management
- dialogue system
- dialogue systems
- disambiguation
- discourse comprehension
- discourse modeling
- discourse understanding
- entity recognition
- hidden markov
- hypothesis verification
- hypothesis verification and selection
- illustration
- information retrieval
- information retrieval tasks
- input understanding
- intention recognition
- k-means
- keyword spotting
- language understanding
- language understanding process
- linear regression
- measuring
- message understanding
- modeling
- multi-modal dialogue
- naive bayes
- named entity recognition
- natural language understanding
- parsing
- part-of-speech tagging
- partitioning
- processing
- pruning
- recognition
- recognition process
- recognition system
- recognition systems
- reference resolution
- regression
- regression algorithm
- semantic tagging
- sense disambiguation
- shallow parsing
- slot-filling
- speech recognition
- speech recognition system
- speech understanding
- spoken dialogue
- support vector regression
- tagging
- transcription
- vector regression
- word sense disambiguation
Other assigned terms:
- ambiguity
- analogy
- anaphora
- annotated corpus
- annotated training corpora
- annotation
- approach
- average error rate
- baseline measure
- case
- classification task
- co-reference
- community
- comprehension
- concept
- concepts
- confidence scores
- contextual knowledge
- corpora
- corpus study
- data set
- dialogue acts
- discourse
- discourse models
- distribution
- domain-specific information
- entropy
- error rate
- evaluations
- f-measure
- fact
- feature
- finite set
- formalisms
- gold standard
- gold standard test
- grammar
- grammar formalisms
- hypothesis
- intention
- interpretation
- kappa
- keyword
- knowledge
- language understanding task
- lexeme
- lexemes
- lexical coverage
- majority class baseline
- mark-up
- measure
- measures
- message
- message understanding conference
- method
- n-gram
- named entities
- named entity
- natural language
- part-of-speech
- perplexity
- posterior
- precision
- priori
- probabilities
- probability
- procedure
- process
- recognition quality
- recognition rate
- recognition task
- relation
- representations
- scalability
- schema
- semantic
- sense-tagged corpus
- slot
- speech recognition performance
- speech recognition task
- spoken language
- spoken language input
- statistics
- stem
- support vector
- task performance
- template element
- template relation
- terms
- test corpora
- test corpus
- test data
- test data set
- test set
- tf \* idf
- tokens
- training
- training corpora
- transcriptions
- tree
- understanding
- understanding process
- user
- utterance
- vocabulary
- word
- word error rate
- word error rates
- word sense
- word senses
- word sequences
- words
