ACL RD-TEC 1.0 Summarization of P01-1004
Paper Title:
LOW-COST, HIGH-PERFORMANCE TRANSLATION RETRIEVAL: DUMBER IS BETTER
LOW-COST, HIGH-PERFORMANCE TRANSLATION RETRIEVAL: DUMBER IS BETTER
Primarily assigned technology terms:
- character-based indexing
- cross validation
- dynamic programming
- indexing
- information retrieval
- japanese information retrieval
- matching
- order-sensitive string comparison
- pre-processing
- scoring
- search
- segmentation
- segmentation system
- sequential correspondence
- splitting
- string comparison
- translation memory
- validation
- vector space model
- weighting
- word-based indexing
Other assigned terms:
- ambiguity
- approach
- case
- characters
- coefficient
- corpora
- correlation
- dice
- edit distance
- evaluation methodology
- fact
- implementation
- input string
- katakana
- key words
- method
- methodology
- morphemes
- precision
- probability
- process
- punctuation
- retrieval performance
- running time
- segment contiguity
- segmentation accuracy
- segments
- source language
- substring
- target language
- term
- terms
- tm system
- translations
- user
- vector space
- word
- word boundaries
- word type
- words
