DARPA TIDES program

related topics
{system, computer, user}
{language, word, form}
{company, market, business}
{theory, work, human}
{island, water, area}

TIDES is an ambitious technology development effort, funded by DARPA. It stands for Translingual Information Detection, Extraction and Summarization. It is focused on the automated processing and understanding of a variety of human language data. The primary goal is to make it possible for English speakers to find and interpret needed information quickly and effectively regardless of language or medium.

Contents

Overview

To provide that overall capability, TIDES is intended to develop a suite of robust, powerful, broadly useful component capabilities; integrate those components effectively in technology demonstration systems; and experiment with the systems on real-world problems. These are all high-risk research activities.

The four component capabilities are

  • Detection – Find or discover needed information.
  • Extraction – Pull out key facts.
  • Summarization – Reduce number of words that someone must read.
  • Translation – Convert text from another language into English.

Detection, extraction, and summarization must work within a language (monolingually) and across languages (translingually) to aid people who speak only English.

In addition to creating effective technology, TIDES aims to develop methods for porting these capabilities rapidly and inexpensively to other languages, including languages having severely limited linguistic resources.

TIDES will integrate its component capabilities with one another and with other technologies to produce synergistic, effective, end-to-end, technology demonstration systems able to address multiple real-world applications.

Investigative Data Warehouse

The FBI's Investigative Data Warehouse contains an "Open Source News Library". This library contains news gathered by the TIDES program. The information is collected from dozens of public websites all over the world, such as Ha'aretz, Pravda, the Jordan Times, The People's Daily, The Washington Post, and others.[1] It uses the MiTAP (Mitre Text and Audio Processing) system.[2]

See also

Notes and Bibliography

Full article ▸

related documents
IBM Lotus SmartSuite
DirectDraw
8-bit clean
Distributed Component Object Model
Electric power control
VESA Display Power Management Signaling
Frequency deviation
Logical Link Control
QSIG
Metropolitan area network
Irssi
TAT-14
Multiplex baseband
TeachText
ARJ
Tape-out
Freescale 683XX
Acme (text editor)
XMMS
PostNuke
Mail transfer agent
Communications in Morocco
COM (hardware interface)
Master station
Telecommunications in France
Relay league
SOAP
Communications in Andorra
Backward channel
Communications in Vietnam