ACL RD-TEC 1.0 Summarization of W04-0106
Paper Title:
INDUCTION OF A SIMPLE MORPHOLOGY FOR HIGHLY-INFLECTING LANGUAGES
INDUCTION OF A SIMPLE MORPHOLOGY FOR HIGHLY-INFLECTING LANGUAGES
Authors: Mathias Creutz and Krista Lugas
Primarily assigned technology terms:
- algorithm
- analyzer
- category tagging
- category-learning
- induction
- learning
- learning task
- linguistica algorithm
- machine translation
- measuring
- morpheme segmentation
- morphological analyzer
- morphology
- morphology induction
- morphology learning
- optimization
- processor
- recognition
- segmentation
- segmentation algorithm
- speech recognition
- splitting
- tagging
- two-level morphology
- unsupervised learning
- vowel lengthening
Other assigned terms:
- affix
- affixes
- allomorphy
- ambiguity
- baseline model
- case
- category structure
- compound words
- corpora
- data set
- data sets
- data sparsity
- development set
- distribution
- evaluations
- f-measure
- fact
- frequency distribution
- gold standard
- length distribution
- lexicon
- linguistic
- meaning
- morph
- morpheme
- morpheme boundary
- morphemes
- natural language
- noise
- parameter values
- part-of-speech
- perplexity
- phrase
- precision
- probabilistic model
- relation
- segments
- semantic
- semantic ambiguity
- set size
- stem
- stems
- suffix
- suffixes
- tags
- test data
- test set
- text
- tokens
- verb
- vowel
- word
- word form
- word structure
- word type
- word types
- words
