ACL RD-TEC 1.0 Summarization of W03-1504

Paper Title:
LOW-COST NAMED ENTITY CLASSIFICATION FOR CATALAN: EXPLOITING MULTILINGUAL RESOURCES AND UNLABELED DATA

Authors: Lluís Màrquez and Adrià de Gispert and Xavier Carreras and Lluís Padró

Other assigned terms:

  • acronym
  • affixes
  • annotated corpus
  • annotation
  • approach
  • binary feature
  • binary features
  • case
  • catalan
  • characters
  • classification error
  • classification model
  • classification problem
  • concept
  • confidence measure
  • context information
  • corpora
  • data set
  • determiners
  • development set
  • dictionary
  • distribution
  • empirical results
  • fact
  • feature
  • gazetteer
  • gazetteer information
  • hand-tagged corpus
  • knowledge
  • knowledge base
  • language change
  • lexical features
  • lexical information
  • lexical knowledge
  • lexical knowledge base
  • lexical resources
  • linguistic
  • linguistic feature
  • local context
  • manual annotation
  • mappings
  • meaning
  • measure
  • measures
  • named entities
  • named entity
  • names
  • nlp tasks
  • person names
  • phrase
  • posterior
  • precision
  • prefixes and suffixes
  • prepositions
  • procedure
  • process
  • punctuation
  • punctuation mark
  • punctuation marks
  • recognition errors
  • recognition module
  • right-hand side
  • seed
  • sentences
  • suffix
  • suffixes
  • synsets
  • technique
  • terms
  • test set
  • text
  • training
  • training data
  • training set
  • translation dictionary
  • translation pairs
  • translations
  • tree
  • trees
  • vocabulary
  • word
  • word form
  • word type
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***