Search Site
 
Advanced Web Demo
Encyclopaedia Britannica’s Cross-Language Morphological Search Plug In Integrates with dtSearch

“We are delighted to partner with dtSearch and provide state of the art foreign language solutions for our customers.”
QuoteSpacer

“Britannica’s morphology  suite seamlessly integrates with the dtSearch Engine developer APIs, enabling users to use English language queries to search for foreign languages, overcoming morphological complexity and ambiguity.”
With a focus on Arabic, Farsi and other Middle Eastern Languages, Encyclopaedia Britannica has developed a rich product suite, which allows English speaking users to review and analyze foreign language source data.  Components of the product suite include Britannica’s Cross Language Morphological Analysis (BMA), Cross Language Entity Extraction (EntX), and Embedded Translation Layer (ETL).

BMA analyzes each word or phrase in the source language, disambiguating and normalizing it to a common form, and produces a common, disambiguated form both in the source language and English and thus enables users to capture, in a single query thousands of complex inflections.  In addition to including a full external thesaurus, BMA also enables cross language search, where users can use English language queries to search in foreign language text.  Britannica’s patent pending ETL is an accurate, context-sensitive English translation of each word or phrase in the searched content, available for Arabic and Farsi.

EntX accurately extracts key words and named entities out of foreign language documents, enabling efficient triage, categorization and concept search.  EntX provides these entities, such as proper names and places, both in their original language and in English.  EntX also supports English user-defined categories, to allow taxonomies and ontology's developed in English to be directly applied to the information in the source languages.

Britannica language analysis suite integrates with dtSearch Engine APIs.  First, the BMA adds morphological capabilities to the indexing and query process.  Second, the BMA’s external thesaurus and ETL can be plugged in through the dtSearch Engine APIs for implementing multilingual synonym and cross-language search. Third, Britannica’s EntX can be integrated with the dtSearch Engine through C++ and Java APIs.  Sample code for all of these levels of integration is available by contacting Britannica.

“We are delighted to partner with dtSearch and provide state of the art foreign language solutions for our customers,” says David Litoff, Director of Business Development, Natural Language Division, Encyclopaedia Britannica.  “Britannica’s morphological suite seamlessly integrates with the dtSearch Engine developer APIs, enabling users to use English language queries to search for foreign languages, overcoming morphological complexity and ambiguity.  All methods enable smooth and transparent integration, adding Britannica’s language capabilities while maintaining the full range of dtSearch’s flexible search capacity.  The transparency of the search integration ensures that any interface provided by dtSearch, whether programmatic or through a graphic UI, is available when using the integrated product.”

“We are very excited to work with Encyclopaedia Britannica’s Natural Language Division,” said Elizabeth Thede, Vice President of Sales.  “Applying Encyclopaedia Britannica’s linguistic expertise will be a great help to dtSearch customers requiring advanced searching of text in Arabic and other Middle-Eastern Languages.”

For a white paper further describing the Encyclopaedia Britannica morphological analysis suite, please see EB-WhitePaper-for-Foreign-language-Analysis.doc

For  additional information on the Encyclopaedia Britannica morphological analysis suite, please visit http://corporate.britannica.com/nlt/
 
Return to Case Study Contents Page
 
Case studies are based on information obtained at the time a case study is written. Case study descriptions may not reflect the current status of an application. dtSearch Corp. cannot independently verify information contained within case studies. All information is provided subject to Terms of Use.