ACL RD-TEC 1.0 Summarization of E06-1047
Paper Title:
PARSING ARABIC DIALECTS
PARSING ARABIC DIALECTS
Authors: David Chiang and Mona Diab and Nizar Habash and Owen Rambow and Safiullah Shareef
Primarily assigned technology terms:
- approximation
- aspect marker
- bikel parser
- error reduction
- expectation maximization
- expectation-maximization
- grammar transduction
- language modeling
- language modeling and parsing
- lattice parsing
- learning
- machine learning
- machine translation
- matching
- modeling
- morphological generation
- msa parser
- nlp
- parser
- parsers
- parsing
- pruning
- reestimation
- sentence splitting
- sentence-transduction
- splitting
- statistical parser
- syntactic analysis
- tokenization
- transduction
- treebank transduction
- tuning
- viterbi
Other assigned terms:
- ambiguity
- anchor
- anchors
- annotation
- approach
- arabic language
- aspectual marker
- backoff
- backoff model
- bias
- case
- composition
- corpora
- demonstrative pronoun
- dependency parse
- dependency parse tree
- dependency trees
- derivation
- derivations
- determiner
- development set
- document
- elementary tree
- experimental results
- f-measure
- fact
- formalism
- formalisms
- function words
- generation
- generation system
- genre
- gold test set
- grammar
- grammar framework
- grammars
- implementation
- knowledge
- la language model
- language model
- language models
- lattice
- lexical items
- lexicon
- linguistic
- linguistic knowledge
- linguistic resources
- mappings
- meaning
- method
- modern standard arabic
- morph
- morphemes
- morphological rules
- msa treebank
- negation
- negative construction
- nonterminal
- nouns
- orthography
- parallel corpora
- parallel corpus
- parallel text
- parse
- parse structure
- parse tree
- parsing model
- parsing problem
- parsing task
- particle
- particles
- phrase
- phrase structure
- phrase structure trees
- pos tag
- precision
- probabilities
- probability
- process
- pronoun
- pronouns
- relation
- root node
- sbar
- semantic
- sentence
- sentences
- standard arabic
- statistics
- stem
- structural information
- suffix
- symbol
- syntactic structure
- tag set
- tags
- terms
- test corpus
- test data
- test set
- text
- text corpora
- tokens
- toolkit
- training
- training data
- transcripts
- transformation
- transformation rules
- translation ambiguity
- translation quality
- tree
- tree-adjoining grammar
- treebank
- trees
- trigram
- trigram language model
- verb
- word
- word form
- word order
- word sequences
- words
