ACL RD-TEC 1.0 Summarization of W06-1631
Paper Title:
CAPTURING OUT-OF-VOCABULARY WORDS IN ARABIC TEXT
CAPTURING OUT-OF-VOCABULARY WORDS IN ARABIC TEXT
Authors: Abdusalam F.A. Nwesri and S.M.M. Tahaghoghi and Falk Scholer
Primarily assigned technology terms:
- algorithm
- approximate string matching
- arabic information retrieval
- categorisation
- classification
- computational linguistics
- cross-lingual information retrieval
- identification
- indexing
- information retrieval
- language identification
- language processing
- machine translation
- matching
- morphological analyser
- n-gram text categorisation
- natural language processing
- processing
- query expansion
- retrieval system
- retrieving
- search
- segmentation
- spelling
- stemmer
- string matching
- text categorisation
- transliteration
- transliteration process
- word segmentation
Other assigned terms:
- affixes
- analyser
- approach
- arabic grammar
- arabic language
- arabic text
- association for computational linguistics
- bigram
- bilingual dictionary
- buckwalter lexicon
- characters
- data set
- dictionaries
- dictionary
- fact
- foreign word
- foreign words
- grammar
- index
- inflection
- intention
- language dictionary
- language model
- language models
- lexicon
- linguistic
- linguistics
- linguists
- meaning
- measure
- method
- n-gram
- n-grams
- names
- natural language
- nouns
- phonemes
- precision
- prefixes and suffixes
- prepositions
- probability
- process
- pronouns
- pronunciation
- proper noun
- queries
- query
- relative frequency
- retrieval performance
- retrieval precision
- right-hand side
- search results
- serbian
- standard arabic
- statistics
- stem
- stems
- stress
- style
- suffix
- suffixes
- term
- terms
- text
- training
- training corpus
- trigram
- unigram
- verb
- vocabulary
- vowel
- word
- word meaning
- words
