ACL RD-TEC 1.0 Summarization of W02-0606
Paper Title:
UNSUPERVISED DISCOVERY OF MORPHOLOGICALLY RELATED WORDS BASED ON ORTHOGRAPHIC AND SEMANTIC SIMILARITY
UNSUPERVISED DISCOVERY OF MORPHOLOGICALLY RELATED WORDS BASED ON ORTHOGRAPHIC AND SEMANTIC SIMILARITY
Authors: Marco Baroni and Johannes Matiasek and Harald Trost
Primarily assigned technology terms:
- affixal morphology
- algorithm
- analyzer
- clustering
- computational linguistics
- computing
- cutoff
- derivational analysis
- editing
- extraction algorithm
- extraction procedure
- extractor
- human language
- human language acquisition
- induction
- induction algorithm
- information retrieval
- iterative procedure
- language acquisition
- latent semantic analysis
- learning
- learning algorithms
- learning program
- linguistic analysis
- matching
- measuring
- morphological analyzer
- morphological analyzers
- morphological learning
- morphological rule extraction
- morphology
- plural formation
- post-processing
- predictor
- processing
- ranking
- re-estimation
- rule extraction
- rule induction
- scoring
- scoring function
- scoring method
- search
- searching
- semantic analysis
- tokenization
- unsupervised learning
Other assigned terms:
- affix
- affixation
- apa corpus
- approach
- association for computational linguistics
- brown corpus
- case
- characters
- cluster
- clusters
- co-occurrence
- co-occurrences
- compounding
- compounds
- computational models
- computational phonology
- content words
- context similarity
- corpora
- corpus frequency
- culture
- derivational morphology
- distance score
- edit distance
- empirical evaluation
- english corpus
- experimental results
- fact
- function words
- german corpus
- gold standard
- grammar
- heuristic
- hypotheses
- implementation
- inflected form
- inflected forms
- inflectional morphology
- interpretation
- knowledge
- latent semantic
- linguist
- linguistic
- linguistics
- maps
- meaning
- measure
- measures
- method
- morpheme
- morphemes
- morphological relatedness
- morphological rule
- morphological rules
- mutual information
- natural language
- noise
- orthographic similarity
- orthographic similarity score
- orthography
- pairs of words
- parse
- parts of speech
- phonetic similarity
- phrase
- precision
- priori
- probabilistic model
- probabilistic models
- probabilities
- procedure
- process
- qualitative analysis
- regular expressions
- search space
- segments
- semantic
- semantic context
- semantic evidence
- semantic information
- semantic relatedness
- semantic similarity
- similarity measure
- similarity score
- similarity scores
- standard deviation
- stem
- stems
- stress
- substring
- suffix
- suffixes
- syntactic patterns
- target language
- tense form
- term
- terms
- test corpora
- test set
- text
- tokens
- transcribed input
- transitivity
- unannotated corpus
- verb
- verb form
- verbal root
- vowel
- word
- word co-occurrence
- word lists
- words
