Cross-lingual C*ST*RD: English access to Hindi information

Anton Leuski, Chin-Yew Lin, Liang Zhou, Ulrich Germann, Franz Josef Och, Eduard H. Hovy

Research output: Contribution to journalArticlepeer-review

Abstract

We present C*ST*RD, a cross-language information delivery system that supports cross-language information retrieval, information space visualization and navigation, machine translation, and text summarization of single documents and clusters of documents. C*ST*RD was assembled and trained within 1 month, in the context of DARPA’s Surprise Language Exercise, that selected as source a heretofore unstudied language, Hindi. Given the brief time, we could not create deep Hindi capabilities for all the modules, but instead experimented with combining shallow Hindi capabilities, or even English-only modules, into one integrated system. Various possible configurations, with different tradeoffs in processing speed and ease of use, enable the rapid deployment of C*ST*RD to new languages under various conditions.
Original languageEnglish
Pages (from-to)245-269
Number of pages25
JournalACM Transactions on Asian Language Information Processing
Volume2
Issue number3
DOIs
Publication statusPublished - 2003

Keywords

  • english access
  • cross-lingual st rd
  • hindi information
  • st rd
  • brief time
  • text summarization
  • new language
  • shallow hindi capability
  • integrated system
  • information space visualization
  • single document
  • surprise language exercise
  • rapid deployment
  • machine translation
  • cross-language information delivery system
  • heretofore unstudied language
  • cross-language information retrieval
  • various possible configuration
  • deep hindi capability
  • different tradeoff
  • various condition
  • english-only module

Fingerprint

Dive into the research topics of 'Cross-lingual C*ST*RD: English access to Hindi information'. Together they form a unique fingerprint.

Cite this