ACL RD-TEC 1.0 Summarization of A00-2035
Paper Title:
TAGGING SENTENCE BOUNDARIES
TAGGING SENTENCE BOUNDARIES
Primarily assigned technology terms:
- algorithm
- boundary determination
- boundary disambiguation
- capitalization
- classification
- classifier
- classifiers
- cross-validation
- decision tree
- decision tree classifier
- decision trees
- disambiguation
- disambiguation problem
- document summarization
- forward-backward algorithm
- hidden markov
- hidden markov models
- identification
- information extraction
- learning
- learning approaches
- lexical lookup
- linear interpolation
- machine learning
- machine learning approaches
- machine translation
- machine-learning
- maximum entropy
- measuring
- name recognition
- neural networks
- parsing
- part-of-speech assignment
- path search
- pos tagger
- pos tagging
- processing
- proper name recognition
- reasoning
- recognition
- regular expression
- rule-based system
- search
- sentence boundary disambiguation
- sentence breaking
- sentence splitting
- spelling
- splitting
- summarization
- syntactic parsing
- tag estimation
- tagger
- taggers
- tagging
- tagging method
- tagging system
- ten-fold cross-validation
- text alignment
- text processing
- tile
- tokenization
- tree classifier
- trigram tagger
- unsupervised training
- viterbi
- viterbi algorithm
- word capitalization
Other assigned terms:
- abbreviation
- abbreviations
- acronym
- adjective
- ambiguity
- annotation
- approach
- bigram
- break
- brown corpus
- case
- characters
- corpora
- document
- entropy
- entropy models
- error rate
- estimation
- fact
- feature
- feature set
- grammars
- heuristic
- heuristics
- implementation
- interpolation
- knowledge
- lexica
- lexical information
- local context
- markov models
- markup
- maximum entropy models
- meaning
- method
- methodology
- n-gram
- n-grams
- names
- nouns
- paragraphs
- parse
- part-of-speech
- part-of-speech tag
- penn treebank
- plural noun
- portability
- pos information
- pos tag
- preposition
- processing tasks
- proper name
- proper names
- proper noun
- punctuation
- schema
- semantic
- semantic classes
- sentence
- sentence boundaries
- sentence boundary
- sentence level
- sentences
- signal
- suffix
- syntactic approach
- syntactic categories
- syntactic category
- syntactic context
- syntactic information
- tagging model
- tagging performance
- tags
- technique
- technologies
- technology
- terms
- text
- tokens
- training
- training data
- tree
- treebank
- trees
- trigram
- unigram
- unlabeled corpus
- verb
- wall street journal corpus
- word
- word corpus
- words
- wsj corpus
- xml format
