To address DARPA's current needs in translingual information extraction, CoGenTex Inc., Cornell University, and the University of Montreal are investigating an integrated approach to the rapid development of translingual information extraction and interactive summarization systems. For an overview of the project, see the RIPTIDES Project Home Page.

CoGenTex's major responsibilities in RIPTIDES are

  • research and development in the area of user-directed multidocument summarization of translated extraction results;
  • research and development of rapidly configurable and portable machine translation of extracted event instances, based on a combination of automated corpus-based and linguistically-based techniques with an emphasis on high-accuracy translation (together with the University of Montreal's RALI group); and
  • RIPTIDES system integration and user interface design and development.

In developing our components of the RIPTIDES system, we plan to take advantage of our Exemplars and RealPro tools, as well as the work-to-date on our Machine Translation project.


  • White, Michael; Cardie, Claire; Han, Chung-hye; Kim, Nari; Lavoie, Benoit; Palmer, Martha; Rambow, Owen; and Yoon Juntae (2000). Towards Translingual Information Access using Portable Information Extraction. In Proceedings of the ANLP/NAACL 2000 Workshop on Embedded Machine Translation Systems, Seattle, WA, pp. 31-37. [Acrobat, 97 Kb]
  • White, Michael; Korelsky, Tanya; Cardie, Claire; Ng, Vincent; Pierce, David; and Wagstaff, Kiri (2001). Multidocument Summarization via Information Extraction. Proceedings of HLT 2001, Human Language Technology Conference, San Diego, CA. [Acrobat, 48 Kb]
  • Lavoie, Benoit; White, Michael; and Korelsky, Tanya (2001). Inducing Lexico-Structural Transfer Rules from Parsed Bi-texts. Proceedings of ACL 2001 Workshop on Data-driven Machine Translation, Toulouse, France, pp. 17-24. [Acrobat, 56 Kb]
  • White, Michael; Cardie, Claire; Ng, Vincent; and McCullough, Daryl (2002). Detecting Discrepancies in Numeric Estimates Using Multidocument Hypertext Summaries. To appear in Proceedings of the Second International Conference on Human Language Technology Research, San Diego, CA. [Acrobat, 186 Kb]
  • White, Michael and Cardie, Claire (2002). Selecting Sentences for Multidocument Summaries using Randomized Local Search. To appear in Proceedings of the ACL 2002 Summarization Workshop, Philadelphia, PA. [Acrobat, 237 Kb]
  • White, Michael; Korelsky, Tanya; Cardie, Claire; Ng, Vincent; Pierce, David; and Wagstaff, Kiri (2001). Detecting Discrepancies and Improving Intelligibility: Two Preliminary Evaluations of RIPTIDES. Proceedings of the 2001 Document Understanding Conference (DUC-2001). [Acrobat, 136 Kb]
  • Lavoie, Benoit; White, Michael; and Korelsky, Tanya (2002). Learning Domain-Specific Transfer Rules: An Experiment with Korean to English Translation. In Proceedings of the COLING 2002 Workshop on Machine Translation in Asia, Taipei, Taiwan, pp. 60-66. [Acrobat, 35 Kb]