ACL RD-TEC 1.0 Summarization of J02-3004
Paper Title:
THE DISAMBIGUATION OF NOMINALIZATIONS
THE DISAMBIGUATION OF NOMINALIZATIONS
Primarily assigned technology terms:
- abductive inference
- algorithm
- ambiguity resolution
- approximation
- back-off smoothing
- class-based smoothing
- classification
- clustering
- coding
- compound interpretation
- compound noun formation
- compound noun interpretation
- computational linguistics
- disambiguation
- disambiguation algorithm
- disambiguation problem
- distance-weighted averaging
- distributional clustering
- encoding
- general-purpose reasoning
- greedy search
- inference process
- information retrieval
- interpretation algorithm
- knowledge bases
- language modeling
- language processing
- learner
- learning
- learning system
- machine learning
- machine translation
- maximum likelihood
- modeling
- natural language processing
- nearest neighbors
- nlp
- nlp systems
- nominalization
- noun interpretation
- noun paraphrasing
- parameter estimation
- parameter tuning
- paraphrasing
- parser
- parsing
- partial parser
- partial parsing
- predictor
- probabilistic learning
- processing
- pseudodisambiguation
- qualitative evaluation
- quantitative evaluation
- reading
- reasoning
- recognition
- reporting
- rule-based approach
- scoring
- scoring system
- search
- search engine
- semantic ambiguity resolution
- semantic disambiguation
- slot filling
- smoothing
- smoothing method
- smoothing techniques
- speech recognition
- statistical methods
- statistical nlp
- subcategorization
- subject analysis
- subject classification
- syntactic analysis
- text compression
- tuning
- unification
- unification-based approach
Other assigned terms:
- adjective
- adjective-noun combination
- ambiguity
- approach
- argument position
- argument structure
- association for computational linguistics
- attachment site
- background information
- bias
- british national corpus
- case
- chance agreement
- chi-square statistic
- classification task
- classification tasks
- cluster
- clusters
- co-occurrence
- co-occurrence count
- co-occurrence frequency
- co-occurrence information
- co-occurrence statistics
- co-occurrences
- coefficient
- compound noun
- compounds
- concept
- concept hierarchy
- concepts
- confusion probability
- contextual features
- contextual information
- corpora
- corpus evidence
- data sparseness
- device
- dictionaries
- dictionary
- disambiguation task
- discourse
- discourse context
- discourse information
- distribution
- distributional information
- distributional similarity
- document
- estimation
- events
- fact
- feature
- feature set
- feature structures
- feature vector
- formalism
- good-turing estimation
- hand-crafted knowledge
- head noun
- human performance
- hypotheses
- information gain
- information sources
- inheritance
- interannotator agreement
- interpretation
- jensen-shannon divergence
- joint probability
- kappa
- kappa coefficient
- knowledge
- knowledge base
- language model
- large corpus
- lexical co-occurrence
- lexical co-occurrence information
- lexical resources
- lexicon
- likelihood
- linguistic
- linguistic constraints
- linguistic information
- linguistic phenomena
- linguistics
- linguistics literature
- logical form
- mapping
- maps
- meaning
- measure
- measures
- method
- methodology
- model parameters
- modifier
- n-gram
- n-gram models
- names
- natural language
- nlp applications
- nlp tasks
- noise
- nominalized compound
- nominals
- norm
- nouns
- opinion
- parameter settings
- parameter values
- paraphrases
- part of speech
- part-of-speech
- parts of speech
- perplexity
- phrase
- pragmatic information
- predicates
- preposition
- prepositional phrase
- prepositional phrases
- prepositions
- probabilistic model
- probabilistic models
- probabilities
- probability
- probability distribution
- probability distributions
- probability value
- procedure
- process
- query
- real-world knowledge
- recipe
- relation
- representations
- schema
- selectional constraints
- selectional restrictions
- semantic
- semantic ambiguity
- semantic information
- semantic knowledge
- semantic relation
- semantic relations
- sentence
- sentences
- sequential rule application
- similarity function
- similarity measure
- similarity measures
- slot
- sparse data
- statistic
- statistical framework
- statistical model
- statistics
- suffix
- suffixes
- symbols
- tags
- taxonomy
- teaching
- terms
- test data
- test set
- text
- thematic role
- thesaurus
- tokens
- training
- training and test data
- training data
- training example
- training set
- transitivity
- tree
- unification formalism
- verb
- vocabulary
- window size
- word
- word sequences
- word similarity
- wordnet
- wordnet taxonomy
- words
- world knowledge
