ACL RD-TEC 1.0 Summarization of J01-2001
Paper Title:
UNSUPERVISED LEARNING OF THE MORPHOLOGY OF A NATURAL LANGUAGE
UNSUPERVISED LEARNING OF THE MORPHOLOGY OF A NATURAL LANGUAGE
Primarily assigned technology terms:
- agglomerative clustering
- algorithm
- approximation
- automatic learning
- automatic morphology
- bootstrap
- bootstrapping
- c + +
- chunking
- clustering
- clustering algorithm
- clustering method
- collapsing
- computational linguistics
- computing
- data compression
- data representation
- data-driven learning
- database
- dictionary construction
- expectationmaximization
- genetic algorithm
- grammar acquisition
- grammatical analysis
- greedy clustering
- identification
- information retrieval
- internet
- language acquisition
- language identification
- learner
- learning
- learning algorithm
- letter-counting
- linguistic analysis
- modeling
- morpheme identification
- morphological analysis
- morphological segmentation
- morphology
- morphology analysis
- morphology learning
- nominalization
- nonconcatenative morphology
- optimization
- ranking
- rating
- reporting
- search
- segmentation
- spelling
- splitting
- suffix identification
- tagger
- terminology
- unsupervised acquisition
- unsupervised learning
- unsupervised learning algorithm
- word analysis
- word segmentation
- word splitting
Other assigned terms:
- adjective
- affix
- affixes
- allomorphy
- ambiguity
- approach
- association for computational linguistics
- bigram
- break
- brown corpus
- case
- chunk
- chunks
- cluster
- clusters
- co-occurrence
- compact representation
- compounds
- computational implementation
- conditional probabilities
- convergence
- corpora
- data structure
- derivational morphology
- device
- dictionary
- dictionary entries
- distribution
- dutch
- edit distance
- english corpus
- english text
- entropy
- evaluation metric
- fact
- formalism
- french
- french word
- generation
- generative grammar
- grammar
- heuristic
- heuristics
- hypotheses
- hypothesis
- hypothesis space
- implementation
- inductive logic
- inflected form
- inflected forms
- inflection
- inflectional morphology
- information theory
- knowledge
- labeling
- language model
- large corpus
- lemma
- lexical category
- lexical item
- lexical items
- lexical representation
- lexicon
- likelihood
- linear order
- linguist
- linguistic
- linguistic pattern
- linguistic theory
- linguistics
- logic
- measure
- medical corpus
- method
- minimum description length
- morpheme
- morpheme boundary
- morphemes
- morphological grammar
- morphological rules
- morphological structure
- mutual information
- n-gram
- n-grams
- names
- natural language
- natural languages
- nouns
- oracle
- orthography
- parse
- phonemes
- precision
- prefixes and suffixes
- probabilistic model
- probabilities
- probability
- procedure
- process
- proper names
- root node
- russian
- segments
- semantic
- semantic relatedness
- size of the corpus
- spoken corpora
- stem
- stems
- style
- substring
- suffix
- suffixes
- surface form
- swahili
- symbol
- syntax
- term
- terminals
- terms
- text
- textbook
- theory
- tone
- training
- training corpus
- trigram
- trigram model
- understanding
- uniform probability
- user
- verb
- verb inflection
- vocabulary
- wall street journal corpus
- word
- word boundaries
- word corpus
- word frequency
- word types
- words
