ACL RD-TEC 1.0 Summarization of W06-1647

Paper Title:
LEXICON ACQUISITION FOR DIALECTAL ARABIC USING TRANSDUCTIVE LEARNING

Authors: Kevin Duh and Katrin Kirchhoff

Other assigned terms:

  • annotated corpora
  • annotation
  • annotation effort
  • annotator
  • approach
  • arabic language
  • association for computational linguistics
  • case
  • characters
  • cluster
  • clusters
  • co-occurrence
  • co-occurrence statistics
  • contextual features
  • conversational telephone speech
  • corpora
  • cosine distance
  • data set
  • data sets
  • development set
  • distance metric
  • distribution
  • estimation
  • fact
  • feature
  • feature vectors
  • frame
  • hypotheses
  • hypothesis
  • joint distribution
  • knowledge
  • labeling
  • lattice
  • learning problem
  • lexical choice
  • lexicon
  • likelihood
  • linguistics
  • manual annotation
  • measure
  • method
  • modern standard arabic
  • morphological information
  • natural language
  • ngram
  • one-vs-rest scheme
  • opinions
  • oracle
  • part-of-speech
  • pos information
  • pos tag
  • precision
  • probabilities
  • probability
  • procedure
  • process
  • sentences
  • standard arabic
  • statistics
  • stem
  • stems
  • support vector
  • svms
  • syntax
  • tag sequence
  • tagging accuracy
  • tags
  • tagset
  • technology
  • term
  • terms
  • test data
  • test set
  • text
  • token frequency
  • tokens
  • training
  • training data
  • training phase
  • training samples
  • training set
  • training text
  • transcriptions
  • transcripts
  • transition probabilities
  • transition probability
  • translation lexicon
  • treebank
  • trigram
  • vocabulary
  • word
  • word sequence
  • word sequences
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***