ACL RD-TEC 1.0 Summarization of J01-1003
Paper Title:
BOOTSTRAPPING MORPHOLOGICAL ANALYZERS BY COMBINING HUMAN ELICITATION AND MACHINE LEARNING
BOOTSTRAPPING MORPHOLOGICAL ANALYZERS BY COMBINING HUMAN ELICITATION AND MACHINE LEARNING
Authors: Kemal Oflazer and Marjorie McShane and Sergei Nirenburg
Primarily assigned technology terms:
- acquisition process
- algorithm
- analyzer
- automatic generation
- automatic learning
- bootstrapping
- bootstrapping morphological analyzers
- character representation
- classifier
- computational linguistics
- computing
- context subsumption
- databases
- disambiguation
- dynamic programming
- dynamic programming scheme
- encoding
- feature mapping
- finite-state transducer
- finite-state transducers
- grammar induction
- human language
- induction
- iterative process
- knowledge elicitation
- language acquisition
- language processing
- language processor
- learner
- learning
- learning algorithm
- learning approach
- learning method
- learning procedure
- learning process
- learning techniques
- lexical acquisition
- lexicon transducer
- machine learning
- machine learning approach
- machine learning techniques
- machine translation
- machine translation systems
- matching
- morphological analysis
- morphological analyzer
- morphological analyzers
- morphological processing
- morphology
- mt system
- natural language processing
- natural language processor
- part-of-speech tagging
- processing
- processor
- reasoning
- recognizer
- regular expression
- rule learning
- rule-learning
- segmentation
- sense disambiguation
- spelling
- spelling correction
- splitting
- statistical learning
- tagging
- transducer
- transducers
- transformation-based learning
- translation systems
- two-level morphology
- unsupervised learning
- unsupervised learning method
- user interface
Other assigned terms:
- affix
- affixation
- affixes
- agglutinating language
- alphabet
- ambiguity
- annotated corpora
- approach
- case
- characters
- citation
- co-occurrence
- compile-time
- composition
- context size
- convergence
- corpora
- data structure
- declarative knowledge
- derivation
- derivations
- dictionary
- distribution
- edit distance
- fact
- feature
- generation
- generation process
- grammar
- heuristic
- infixation
- inflected form
- inflected forms
- inflection
- inflectional information
- knowledge
- language processing applications
- learning module
- learning paradigm
- lexical item
- lexical representation
- lexicon
- linguist
- linguistic
- linguistic information
- linguistics
- mapping
- maps
- meaning
- measure
- measures
- method
- minimum description length
- morpheme
- morpheme boundary
- morphemes
- morphological ambiguity
- morphological features
- morphological information
- morphological lexicon
- morphological rules
- names
- natural language
- natural language processing applications
- noise
- nominals
- nouns
- parameter values
- part of speech
- part-of-speech
- phonemes
- phonological rules
- procedure
- process
- regular expressions
- representations
- rewrite rules
- rule format
- run-time
- segments
- source language
- static knowledge
- stem
- stems
- substring
- subsumption
- suffix
- suffixes
- surface form
- symbol
- symbols
- tags
- technique
- term
- test corpus
- test data
- test set
- text
- tokens
- transformation
- transformation rules
- user
- vowel
- vowel harmony
- word
- word boundaries
- word boundary
- word form
- word formation
- words
