acm-header
Sign In

Communications of the ACM

ACM TechNews

Scientists Work to Automate Quick Translation of Obscure Languages


View as: Print Mobile App Share:
University of Southern California researchers will use Tagalog and Swahili to test their translation tool.

Researchers in the University of Southern California's Information Sciences Institute are developing an automated tool for translating obscure languages into English.

Credit: iStock

Researchers at the University of Southern California's Information Sciences Institute (ISI) have received a U.S. Intelligence Advanced Research Projects Activity grant to develop an automated tool for translating obscure languages under the Summarization and domain-Adaptive Retrieval (SARAL) project.

"The overall objective is to provide a Google-like capability, except the queries are in English, but the retrieved documents are in a low-resource foreign language," says ISI team leader Scott Miller. "The aim is to retrieve relevant foreign-language documents and to provide English summaries explaining how each document is relevant to the English query."

SARAL will begin by compiling documents in test languages, including speech, online documents, and video clips, which have been translated into English. The team will then develop algorithms to analyze language patterns and morphology, and the tool will be designed to respond to domain-specific queries, generating a summarized response of about 100 words describing the result's relevance to the search.

From USC News
View Full Article

 

Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account