The Defense Advanced Research Projects Agency awarded a $7.1 million contract to SRI International to start building the latest in a long line of technologies that seek to translate and understand multiple languages.
In the news: The fantastic world of steampunk technology
DARPA's Broad Operational Language Translation (BOLT) program seeks to create technology capable of translating into English multiple foreign languages in all genres including informal speech and text such as occurs in email, messaging and conversational speech, retrieve information from the translated material and allow bilingual communication via speech or text.
DARPA says the BOLT systems should include:
- The capability for human-machine communication by voice in English and Arabic using multi-modal input for robotic control or desk-top applications
- The capability to handle multi-turn, bilingual human-human conversation in speech or text including a monolingual human-machine dialogue in both languages for clarification
- The capability to retrieve targeted information from multi-lingual sources using natural language English queries with human-machine clarification and disambiguation dialogue and means to annotate documents (textual or spoken) for fast comprehensive search
- Research in deep semantic language acquisition using robotic visual and tactile information as input for experiential learning of objects, actions, and consequences
- Research in basic technologies such as parsing, Semantic Role Labeling (SRL), language modeling, etc. that are essential to the success of the program.
For its part, SRI said it will lead research activities with the goal of developing systems that accurately translate foreign languages and extract information regardless of genre and media. Such technologies are intended to facilitate bilingual conversations with instant interpretation and automatic clarification.
SRI said it has a strong record of delivering breakthrough technologies in artificial intelligence and complex language-processing systems for DARPA. Decades of SRI research in artificial intelligence, including leadership of the largest known artificial intelligence project in US history (CALO), led to the development of the groundbreaking virtual personal assistant technology called Siri. Siri was acquired from SRI by Apple in 2010.
SRI's speech and translation work includes research under DARPA's Global Autonomous Language Exploitation (GALE) program to develop computer software that translates and analyzes huge volumes of speech and text in multiple languages, and under the Spoken Language Communication and Translation System for Tactical Use (TRANSTAC) program to enable two-way communication between US warfighters and speakers of other languages, SRI said.
SRI said it will include engineers from Columbia University's Engineering School, Queens College City University of New York, University of Edinburgh, Hong Kong University of Science and Technology R&D Corporation Limited, Estuate Incorporated, Oregon Health & Sciences University, University of Washington, University of Rochester, University of Massachusetts, Aix-Marseille University/National Center for Scientific Research (CNRS), and University of Texas at Dallas in BOLT development.
The development of language technology has been hot of late. Just this week DAPA will detail what it calls Deep Exploration and Filtering of Text (DEFT) which is the union of advanced technologies from artificial intelligence, computational linguistics, machine learning, natural-language fields it hopes to bring together to build an automated system that will let analysts and others better grasp meanings from large volumes of text documents.
From DARPA: "Automated, deep natural-language understanding technology may hold a solution for more efficiently processing text information. When processed at its most basic level without ingrained cultural filters, language offers the key to understanding connections in text that might not be readily apparent to humans. Sophisticated artificial intelligence of this nature has the potential to enable defense analysts to efficiently investigate orders of magnitude more documents so they can discover implicitly expressed, actionable information contained within them."
Technology developed within the DEFT program is expected to provide the capability to identify and interpret both explicit and implicit information from highly ambiguous and vague narrative text, and integrate individual facts into large domain models for assessment, planning and prediction, DARPA stated.
Meanwhile another innovative language project, called Autonomous Dynamic Analysis of Metaphor and Analogy, or ADAMA, aims to build a software system that can automatically analyze metaphorical speech in five different languages by analyzing huge quantities of online data got off the ground this month when the US Army Research Laboratory awarded a $1.4 million contract to the team conducting the research.
Related: 7 high-tech programs that want to pick your brain
The research is backed by the US Intelligence Advanced Research Projects Activity (IARPA), which develops high-risk, reward research projects for the government, and is intended to build a repository of speech metaphors from American/English Iranian Farsi, Mexican Spanish and Russian speakers. ADAMA could have immediate applications in forensics, intelligence analysis, business intelligence, sociological research and communication studies, researchers stated.
From IARPA: "Metaphors have been known since Aristotle as poetic or rhetorical devices that are unique, creative instances of language artistry (for example: The world is a stage; Time is money). Over the last 30 years, metaphors have been shown to be pervasive in everyday language and to reveal how people in a culture define and understand the world around them," IARPA says.
One of the key goals of the program is to get at the deeper meanings found in metaphoric and figurative language to better understand messages and intentions of people from communities all over the world, said Shlomo Argamon an associate professor of Computer Science with the Illinois Institute of Technology who is heading up the research team. That team includes researchers from Massachusetts Institute of Technology, Georgetown University; Ben-Gurion University of the Negev, Bar-Ilan University, the Center for Advanced Defense Studies.
Follow Michael Cooney on Twitter: nwwlayer8 and on Facebook
Layer 8 Extra
Check out these other hot stories:
US grabs more domain names, $1.4 million from online counterfeit operations
FBI Chief: On technology, insider threats and cyber criminals
US sets $1.4M to get unique metaphor-recognizing software system humming
Air Force offers 111 airmen for NASA astronaut duty
DHS looking for forensic tools to lift evidence from solid state drives
DARPA system to blend AI, machine learning to understand mountain of text
CISOs morph into soothsayers, managers of double-digit security spending increases
Do you really need a social media will?
The sizzling world of asteroids
Fabulous space photos from NASA's Hubble telescope
IBM melds crime-fighting, big data analytics in one security package
IBM targets mobile, BYOD customers with cloud software, security services
Forget those fancy mega yachts - military auctioning DARPA's super stealth boat
Notion of extraterrestrial life more whimsical than factual?
On the trail of NASA's space potty