Linguistic Agents: Smart Software from Israel

April 16, 2008

In my new study “Beyond Search”, I profile a number of non-US content processing companies. Several years ago I learned about Jerusalem-based Linguistic Agents. The company uses an interesting technique for its natural language processing system. I found Linguistics Agents’ approach interesting.

The firm’s founder is Sasson Margaliot. In 1999, Mr. Margaliot wanted to convert linguistic theories
into practical technologies. The goal was to enable computers to understand human language and context. Like other innovators in content processing, Mr. Margaliot had expertise in theoretical linguistics and application software development. He studied Linguistics at UCLA and Computer Science at Hebrew
University of Jerusalem.

The company’s chief scientist is Alexander Demidov. Mr. Demidov was responsible for the development of Linguistic Grammars for the Company’s NanoSyntactic Parser, the precursor of today’s Streaming Logic engine. Previously, he worked for the Moscow Institute of Applied Mathematics and at Zehut, a company that developed advanced compression and protection algorithms for digital imaging.

Computerworld identified the company in the summer of 2007 as having one of the “cool cutting-edge technologies on the horizon”. Since that burst of publicity in the US, not much has been done to keep the company’s profile above the water line.

The company uses “nano syntax” to extract meaning from documents. On the surface, the approach seems to share some features with Attensity, the “deep extraction company” and the firm that I included in my new study as an exemplar of recursive analysis and linguistic processing for meaning.

The idea is that a series of parallelized processes converts a sentence into a representation that preserves its syntactical meaning. The technology can be applied to search as well as context-based advertising. The company asserts, “The technology can revolutionize how computers and people interact –computers will learn our language instead of vice versa.”

Linguistic Agents’ language solution can be used for front-end, back-end or inter computer communication application development. The technology can be used at any one of the three layers independently or in conjunction with one another to create an advanced intelligent linguistic enabled application.

The platform can be used in several different ways:

  • Search engines can be given a new lease on life with the company’s concept identification function and NLP service.
  • NLP queries can be used for behind-the-firewall and Web search
  • Filtering and routing services can respond to end-user queries written in human language.
  • Interactive functions can be added to games, educational software and online environments via human language understanding integrated with voice recognition software solutions.

The diagram below provides a schematic overview of how the system operates:

Linguistic Agents\' architecture

Several observations are warranted. First, innovation in content processing is not confined to the United States. It is true that many of the people commercializing advanced content processing systems studied in the US, some of these entrepreneurs are growing their companies outside the US. Second, natural language processing or NLP is starting to enter the mainstream of search and retrieval. This is due in part to more potent CPUs and declining memory costs. NLP remains a computational task with an enormous appetite for resources. Third, key word search does not meet user needs. NLP allows the user to write or speak to a computing device instead of figuring out key words and scanning laundry lists of results in search of a match that answers the user’s question.

For more information about the company, navigate to Linguistics Agents’ Web site.

Stephen Arnold, April 16, 2008

Comments

Comments are closed.

  • Archives

  • Recent Posts

  • Meta