ACL RD-TEC 1.0 Summarization of W06-1630
Paper Title:
UNSUPERVISED NAMED ENTITY TRANSLITERATION USING TEMPORAL AND PHONETIC CORRELATION
UNSUPERVISED NAMED ENTITY TRANSLITERATION USING TEMPORAL AND PHONETIC CORRELATION
Authors: Tao Tao and Su-Youn Yoon and Andrew Fister and Richard Sproat and ChengXiang Zhai
Primarily assigned technology terms:
- alignment-scoring technique
- bootstrapping
- bootstrapping method
- candidate generation
- candidate scoring
- computational linguistics
- databases
- entity recognition
- entity recognition and transliteration
- entity recognizer
- entity transliteration
- festival textto-speech system
- generation method
- induction
- information retrieval
- iterative bootstrapping
- language processing
- learner
- learning
- machine learning
- matching
- method combination
- morphological induction
- name transliteration
- named entity recognition
- named entity transliteration
- named-entity recognizer
- natural language processing
- orthographic representation
- pearson correlation
- phonetic transliteration
- phonetic-based scoring
- processing
- ranking
- recognition
- recognizer
- score combination
- scoring
- scoring method
- sentence alignment
- string-alignment
- textto-speech
- textto-speech system
- transliteration
- tuning
Other assigned terms:
- affix
- approach
- association for computational linguistics
- case
- characters
- clusters
- coefficient
- comparable corpora
- corpora
- correlation
- correlation coefficient
- correlations
- data set
- dictionary
- distribution
- document
- edit distance
- empirical results
- english corpus
- english text
- evaluation set
- fact
- feature
- french
- frequency distribution
- generation
- hindi
- jensen-shannon divergence
- knowledge
- language pairs
- lexicon
- linear combination
- linguistics
- mandarin chinese
- measure
- measures
- method
- middle eastern languages
- named entities
- named entity
- named-entity
- names
- natural language
- orthography
- pearson correlation coefficient
- phoneme
- phonemes
- phonetic similarity
- pinyin
- pronunciation
- query
- query vector
- sentence
- source language
- statistics
- suffix
- target language
- target languages
- technique
- term
- test set
- text
- toolkit
- topics
- training
- transcriptions
- translations
- word
- words
