Xerox Rolls Out Semantics-Based Search for Researchers

Xerox Corp. says its new search engine based on semantics will analyze the meaning behind questions and documents to help researchers find information more quickly.

FactSpotter promises to help by returning a specific portion of a search document that is relevant to the query.

Developing the search engine is similar to understanding how brains process information, said Frederique Segond, manager of parsing and semantics research at Xerox Research Center Europe in Grenoble, France.

"Many words can be different things at the same time. The context makes the difference," she said. "The tricky things here are not the words together but how are they linked."

For example, common searches using keywords "Lincoln" and "vice president" likely won't reveal President Abraham Lincoln's first vice president. A semantic search should yield the answer: Hannibal Hamlin.

Segond, whose background is in math and linguistics, said Stamford-based Xerox has been working on the project for four years.

FactSpotter was introduced in Grenoble on Wednesday and will launch next year, initially to help lawyers and corporate litigation departments plow through thousands of pages of legal documents. Xerox expects the technology to eventually be used in health care, manufacturing and financial services.

Xerox's technology is part of a growing field in which researchers are trying to adapt to a computer the complex workings of the brain.

Riza C. Berkan, chief executive of search company Hakia Inc. in New York, said researchers are using principles of human thought as it relates to language "to change search engines from stupid machines into intelligent and smart."

"All searches today are at the tip of iceberg," he said. "The bottom of the iceberg is when you ask the complicated questions."