ACL RD-TEC 1.0 Summarization of P00-1026
Paper Title:
A MORPHOLOGICALLY SENSITIVE CLUSTERING ALGORITHM FOR IDENTIFYING ARABIC ROOTS
A MORPHOLOGICALLY SENSITIVE CLUSTERING ALGORITHM FOR IDENTIFYING ARABIC ROOTS
Authors: Anne N. De Roeck and Waleed Al-Fares
Primarily assigned technology terms:
- algorithm
- arabic ir
- automatic classification
- automatic indexing
- classification
- classification algorithm
- clustering
- clustering algorithm
- conversational system
- differential weighting
- editing
- finite state
- finite state transducer
- grouping
- identification
- indexing
- information retrieval
- information retrieval system
- link clustering
- morpho-syntactic analysis
- morphology
- nlp
- parsers
- processing
- recognition
- retrieval system
- root identification
- root-based clustering
- sampling
- search
- single word clustering
- single-link clustering
- spelling
- transducer
- weighting
- word clustering
Other assigned terms:
- affix
- affixes
- approach
- arabic morphology
- arabic text
- benchmark
- bias
- case
- characters
- cluster
- clusters
- data set
- data sets
- datr
- derivation
- derivations
- dice
- dictionaries
- dictionary
- distribution
- evaluation data
- evaluation measure
- formalisms
- function words
- grammatical function
- heuristic
- heuristic rules
- index
- inflectional language
- interpretation
- knowledge
- large corpus
- lexical resources
- lexicon
- meaning
- measure
- method
- morphological knowledge
- morphological relatedness
- morphological variation
- n-gram
- n-grams
- orthography
- pair similarity
- parse
- precision
- prefixes and suffixes
- prepositions
- process
- pronouns
- stem
- stems
- substring
- suffix
- suffixes
- symbol
- technique
- terms
- text
- training
- vowel
- word
- word boundaries
- word boundary
- word pair
- word pair similarity
- words