ACL RD-TEC 1.0 Summarization of P06-1084

Paper Title:
AN UNSUPERVISED MORPHEME-BASED HMM FOR HEBREW MORPHOLOGICAL DISAMBIGUATION

Authors: Meni Adler and Michael Elhadad

Other assigned terms:

  • acoustic likelihood
  • affix
  • affixes
  • ambiguity
  • ambiguous words
  • annotated corpus
  • approach
  • arabic corpora
  • arabic morphology
  • association for computational linguistics
  • backoff
  • case
  • chunk
  • complex word
  • confusion matrix
  • contextual information
  • corpora
  • data set
  • data sparseness
  • data sparseness problem
  • dictionary
  • disambiguation system
  • distribution
  • english text
  • estimation
  • experimental results
  • fact
  • generation
  • grammar
  • hand-crafted grammar
  • hebrew corpus
  • hierarchical model
  • hmm model
  • index
  • interpretation
  • knowledge
  • language model
  • large scale corpus
  • lattice
  • lemma
  • lexemes
  • lexical items
  • lexicon
  • likelihood
  • linguistic
  • linguistics
  • method
  • modern hebrew
  • morpheme
  • morphemes
  • morpho-lexical probabilities
  • morphological features
  • mwes
  • named entity
  • names
  • nouns
  • phrase
  • probabilistic model
  • probabilities
  • probability
  • procedure
  • process
  • proper names
  • sentence
  • sentence representation
  • sparseness problem
  • static knowledge
  • statistics
  • stochastic model
  • supervised model
  • symbol
  • symbols
  • syntactic constraints
  • tag set
  • tagged corpus
  • tagged text
  • tags
  • tagset
  • term
  • test corpus
  • text
  • time complexity
  • trained model
  • training
  • training corpora
  • training corpus
  • transformation
  • transition probabilities
  • uniform distribution
  • unknown word model
  • untagged corpus
  • word
  • word formation
  • word formation rules
  • word model
  • word type
  • word types
  • word-based model
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***