ACL RD-TEC 1.0 Summarization of W02-1030
Paper Title:
USING THE WEB TO OVERCOME DATA SPARSENESS
USING THE WEB TO OVERCOME DATA SPARSENESS
Authors: Frank Keller and Maria Lapata and Olga Ourioupina
Primarily assigned technology terms:
- bracketing
- chart parser
- chunk parser
- chunker
- class-based smoothing
- computational linguistics
- correlation analysis
- disambiguation
- distance-weighted averaging
- example-based machine translation
- gsearch
- heuristic method
- language processing
- learning
- learning algorithms
- linear interpolation
- machine translation
- magnitude estimation
- matching
- mining
- morphology
- nlp
- parser
- partial parser
- predictor
- processing
- querying
- retrieving
- sampling
- search
- search engine
- search engines
- sense disambiguation
- shallow analysis
- similarity-based smoothing
- smoothing
- smoothing techniques
- task-based evaluation
- web search
- word sense disambiguation
Other assigned terms:
- adjective
- ambiguity
- approach
- association for computational linguistics
- bias
- bigram
- british national corpus
- case
- chunk
- co-occurrence
- co-reference
- coefficient
- compounds
- context free grammar
- corpora
- corpus evidence
- corpus frequency
- correlation
- correlation coefficient
- correlations
- data set
- data sets
- data sparseness
- data sparseness problem
- determiner
- determiners
- dictionary
- empty string
- estimation
- fact
- french
- grammar
- heuristic
- heuristics
- human judgments
- hypothesis
- inflectional morphology
- interpolation
- linguistic
- linguistic phenomenon
- linguistics
- measure
- method
- nlp tasks
- noise
- nouns
- part of speech
- pp attachment
- predicate-argument
- procedure
- process
- proper name
- queries
- query
- search term
- sense ambiguity
- sentence
- sparseness problem
- statistics
- syntactic patterns
- syntactic variation
- tagged corpus
- technique
- term
- terms
- text
- training
- training set
- translations
- verb
- webexp software package
- word
- word sense
- wordnet
- words
