ACL RD-TEC 1.0 Summarization of P95-1032
Paper Title:
A PATTERN MATCHING METHOD FOR FINDING NOUN AND PROPER NOUN TRANSLATIONS FROM NOISY PARALLEL CORPORA
A PATTERN MATCHING METHOD FOR FINDING NOUN AND PROPER NOUN TRANSLATIONS FROM NOISY PARALLEL CORPORA
Primarily assigned technology terms:
- algorithm
- backtracking
- bilingual lexicon compilation
- candidate evaluation
- computing
- corpus alignment
- distance function
- dynamic time warping
- em-based word alignment
- fast matching
- lexicon acquisition
- lexicon compilation
- lexicon-based alignment
- machine translation
- machine-aided translation
- machine-aided translation system
- matching
- noise elimination
- pattern matching
- pattern recognition
- pattern recognition technique
- pos tagger
- recognition
- rough alignment
- sentence alignment
- smoothing
- supervised training
- tagger
- tagging
- text alignment
- thresholding
- time warping
- tokenizer
- translation system
- translation systems
- translator
- transliteration
- vector representation
- word alignment
- word translation
Other assigned terms:
- anchor
- bilingual lexicon
- bilingual lexicons
- boundary information
- case
- characters
- chinese characters
- chinese text
- chinese translation
- chinese word
- chinese words
- chunk
- chunks
- compound noun
- compound words
- compounds
- confidence measure
- confidence score
- corpora
- corpus size
- correlation
- dictionaries
- dictionary
- document
- domain-specific noun
- english text
- euclidean distance
- evaluations
- fact
- governor
- idiom
- japanese translation
- knowledge
- language pairs
- lexicon
- linguistic
- linguistic information
- literal translation
- local maxima
- mapping
- matching process
- meaning
- measure
- method
- mutual information
- mutual information score
- names
- noise
- noun phrases
- nouns
- pairs of words
- parallel corpora
- parallel corpus
- parallel text
- parallel texts
- precision
- priori
- procedure
- process
- proper names
- proper noun
- representations
- segments
- sentence
- sentence boundaries
- sentence boundary
- slang
- technique
- term
- terms
- test corpus
- text
- text segments
- training
- translations
- window size
- word
- word frequency
- word pair
- words
