ACL RD-TEC 1.0 Summarization of H05-1105
Paper Title:
USING THE WEB AS AN IMPLICIT TRAINING SET: APPLICATION TO STRUCTURAL AMBIGUITY RESOLUTION
USING THE WEB AS AN IMPLICIT TRAINING SET: APPLICATION TO STRUCTURAL AMBIGUITY RESOLUTION
Authors: Preslav Nakov and Marti Hearst
Primarily assigned technology terms:
- algorithm
- ambiguity resolution
- bracketing
- capitalization
- classifiers
- compound bracketing
- computational linguistics
- computing
- database
- decision tree
- dependency parser
- disambiguation
- disambiguation problem
- evidence combination
- human language
- human language technology
- identification
- interfaces
- language processing
- language technology
- learning
- learning method
- lexical disambiguation
- maximum entropy
- maximum entropy model
- natural language processing
- nlp
- noun compound bracketing
- paraphrasing
- parser
- parsers
- post-processing
- pp-attachment ambiguity resolution
- processing
- querying
- reading
- search
- search engine
- search engines
- sentence simplification
- smoothing
- spanish disambiguation
- structural disambiguation
- supervised back-off
- supervised method
- syntactic analysis
- transformation-based learning
- unsupervised method
- web search
- web search engine
Other assigned terms:
- adjective
- adverb
- ambiguity
- approach
- association for computational linguistics
- back-off model
- benchmark
- bigram
- british national corpus
- case
- characters
- co-occurrence
- co-occurrence statistics
- collocation
- conceptual association
- conjunct
- coordination conjunction
- corpora
- data sparseness
- data sparseness problem
- determiner
- determiners
- distributional information
- ellipsis
- entropy
- events
- fact
- feature
- head noun
- head word
- heuristic
- heuristics
- human performance
- inflected forms
- information sources
- labeled training data
- labeling
- large corpora
- large corpus
- lexical items
- linguistics
- local context
- meaning
- method
- modifier
- mutual information
- n-gram
- n-gram model
- n-gram models
- n-grams
- natural language
- nlp tasks
- noun phrase
- nouns
- number agreement
- ontologies
- paraphrase
- paraphrases
- parsed corpus
- part-of-speech
- part-of-speech tags
- penn treebank
- phrase
- phrase attachment
- pp-attachment
- pp-attachment ambiguity
- precision
- preposition
- prepositional phrase
- prepositional phrase attachment
- prepositional phrases
- priori
- probabilities
- pronoun
- pronouns
- punctuation
- queries
- query
- relation
- semantic
- semantic classes
- sentence
- sentences
- signal
- sparseness problem
- statistics
- structural ambiguity
- surface pattern
- symbol
- symbols
- synsets
- tags
- taxonomy
- technique
- technology
- terms
- test set
- text
- text corpus
- thesaurus
- training
- training data
- training set
- tree
- treebank
- trees
- understanding
- verb
- verb attachment
- wildcard
- word
- word classes
- word sequences
- word-net
- wordnet
- wordnet synsets
- words
