ACL RD-TEC 1.0 Summarization of W03-1506

Paper Title:
MULTI-LANGUAGE NAMED-ENTITY RECOGNITION SYSTEM BASED ON HMM

Authors: Kuniko Saito and Masaaki Nagata

Other assigned terms:

  • alphabet
  • ambiguity
  • approach
  • back-off model
  • bigram
  • bigram model
  • bilingual dictionaries
  • bilingual lexicon
  • bilingual lexicons
  • case
  • character type
  • characters
  • compound words
  • corpora
  • dictionaries
  • dictionary
  • entropy
  • function words
  • generation
  • graph structure
  • ibm model
  • input string
  • interpolation
  • interpolation scheme
  • joint probability
  • kanji
  • katakana
  • language model
  • lexicon
  • meaning
  • measure
  • method
  • morpheme
  • multi-language named-entity
  • named entities
  • named entity
  • named-entity
  • named-entity task
  • names
  • nouns
  • parallel text
  • parallel texts
  • part of speech
  • part-of-speech
  • personal names
  • phrase
  • probabilities
  • probability
  • process
  • recognition model
  • segmentation ambiguity
  • sentence
  • sentences
  • sparse data
  • sparse data problem
  • statistical language model
  • substring
  • support vector
  • symbol
  • symbols
  • tagged corpora
  • target language
  • technique
  • terms
  • text
  • training
  • training data
  • translation model
  • translation probability
  • vowel
  • word
  • word bigram model
  • word boundary
  • word candidate
  • word segmentation ambiguity
  • word sequence
  • word sequence length
  • word sequences
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***