ACL RD-TEC 1.0 Summarization of N06-1011
Paper Title:
NAMED ENTITY TRANSLITERATION AND DISCOVERY FROM MULTILINGUAL COMPARABLE CORPORA
NAMED ENTITY TRANSLITERATION AND DISCOVERY FROM MULTILINGUAL COMPARABLE CORPORA
Authors: Alexandre Klementiev and Dan Roth
Primarily assigned technology terms:
- algorithm
- bootstrap
- classification
- coupling
- crawling
- discriminative approach
- discriminative learning
- entity recognition
- entity transliteration
- identification
- information extraction
- iterative algorithm
- iterative training
- language processing
- learning
- learning framework
- learning techniques
- machine learning
- machine learning techniques
- matching
- morphology
- named entity recognition
- named entity transliteration
- natural language processing
- ne discovery
- ne extraction
- ne transliteration
- nlp
- perceptron
- preprocessing
- processing
- recognition
- scoring
- scoring function
- sequence matching
- sequence scoring
- thresholding
- time sequence scoring
- transliteration
- word alignment
Other assigned terms:
- aligned corpus
- approach
- approach to transliteration
- bilingual corpora
- case
- coefficient
- comparable corpora
- comparable corpus
- corpora
- dictionary
- distance metric
- distribution
- empty string
- feature
- feature vector
- generation
- generative model
- generative models
- hand-tagged corpus
- knowledge
- language knowledge
- language processing tasks
- likelihood
- linear model
- method
- named entities
- named entity
- natural language
- natural language processing tasks
- news corpus
- news web site
- phonetic sequence
- positive and negative examples
- processing tasks
- running time
- russian
- scoring metric
- set size
- signal
- similarity function
- similarity score
- sources of information
- substring
- target language
- training
- training example
- training examples
- training set
- translations
- transliteration candidate
- transliteration model
- untagged corpora
- web page
- web site
- word
- words
