Come Hear Us Speak at DODIIS
We’re pleased to have been selected to speak at the 2012 DoDIIS Worldwide Conference—the premier conference for the U.S. Defense Intelligence Agency—that is coming up May 1-4 in Denver, CO.
Translating names from critical languages such as Arabic, Pashto, and Dari to English needs to be accurate, quick, and consistent, but the task is tedious and error-prone for human translators do it. Depending on the translation standard, should the Tunisian poet’s name be translated to “Abu-al-Qasim al-Shabbi” or “Aboul-Qacem Echebbi”? On Monday, April 2, Jennifer Flather and Joel Ross will be talking about the Highlight language analysis suite which takes care of translating names in these languages, so that valuable human translators can focus on translating content. (See details below.)
Tuesday afternoon, Steve Kearns and Jeff Godbold tackle the continuing hot issue of “big data” and how to get intelligence from volumes and volumes of text—including text in foreign languages— that threaten to overwhelm those working with OSINT, DOCEX, and DOMEX. They will discuss text analytics tools which have found success in the “early” big data domains of web and enterprise search engines.
We hope you’ll come by to hear these wonderful talks!
Monday, April 2, 2012
No Names Left Behind: Better and Faster Arabic, Pashto, and Dari Name Translation
Speakers: Jennifer Flather, Program Manager, Desktop Tools and Joel Ross, VP, Defense and Intelligence Services
When: 1:35-2:20 pm
Where: Breakout session 507
Making the right connections hinges on linking data from disparate sources. Frequently the link may be a person or place, so something as simple as a mistranslated name will cause a search to miss relevant documents. The name translation and standardizing component of the Highlight language analysis suite ensures fast and reliable translation of names from Arabic, Pashto, and Dari according to a number of government transliteration standards. In the field, Highlight has reduced average translation time of a name from 10 seconds to 3 seconds, a production increase of over 300%.
This talk will introduce the components of Highlight—available to IC users via ODNI—through problem-solving scenarios, such as forensic processing of digital media to extract and translate personal names, and deciphering personal names from a visitor request form.
Tuesday, April 3, 2012
Intelligence From Raw Data: Applying Text Analytics to Save Time and Lives
Speakers: Steve Kearns, Director of Product Management and Jeff Godbold, Director of Federal Solutions
When: 1:15-2 pm
Where: Breakout session 507
“Information overload” and “big data” are cliché phrases, but the truth is that the volume and velocity of data is growing faster than ever and it must be triaged by the same or fewer analysts. When presented with massive volumes of semi-structured, multilingual data from many sources, how do you rapidly discover relevant data and efficiently move it into the analytical process? This talk will discuss how advanced text analytics—entity extraction, entity searching, document clustering, near duplicate detection, and fact-relationship-event extraction—can be combined with a powerful search engine to facilitate information discovery and thematic analysis across a variety of sources and languages.
We will demonstrate how this technology can provide new ways to search, navigate, and explore large data sets to optimize the triage process and locate actionable intelligence from volumes of multilingual text.