Basis Technology's Natural Language Processing Software for Search Applications Adds 13 Languages
Rosette(R) Linguistics Platform Version 7.4 Supports More European Languages, Indonesian, and Malay
(firmenpresse) - CAMBRIDGE, MA -- (Marketwire) -- 10/04/11 -- Basis Technology Corporation (), the leading provider of natural language processing software for search-based applications, is now shipping the version 7.4, which adds 13 languages. Search engines and text processing applications incorporating Rosette can instantly analyze 40 languages. The newly added languages are Albanian, Bulgarian, Catalan, Croatian, Estonian, Indonesian, Latvian, Malay, Norwegian, Serbian, Slovak, Slovenian, and Ukrainian.
For the supported languages, Rosette returns the dictionary form of each word, enabling search engines to match all occurrences of keywords regardless of the word form. Thus, searching for the verb "spoke" in English would also find occurrences of "speak", "speaking", and "speaks."
"Basis Technology is continually expanding the coverage and capabilities of our linguistic software, because it forms the foundation of relevant and accurate search in many languages," said Steve Kearns, Product Manager at Basis Technology. "Rosette provides a wide range of text analysis functionality in one package that is the choice of search industry leaders and new startups alike."
Rosette 7.4 is available now for evaluation. Contact Basis Technology for license and pricing information at +1-617-386-2090 or .
Rosette's natural language processing components integrate into software applications to add multilingual capability to search and retrieval, business intelligence, e-discovery, digital forensics, and financial compliance applications.
The determines the written language and character encoding of each indexed document, and is capable of recognizing 55 languages and 45 encodings. tokenizes and lemmatizes text in 40 languages at index or query time. Determining the "lemma" -- i.e., dictionary form -- of each indexed word sharpens search engine relevancy. This technique enables queries containing, for example, the word "children" to match documents containing the word "child." The automatically extracts "entities" -- e.g., names of people, places, and organizations -- to enable document clustering and faceted search.
The quickly and accurately translates Middle Eastern and Asian Names to English. The resolves name variations despite spelling and language differences.
Basis Technology () is a leading provider of text analytics technology and digital forensics solutions. The platform provides linguistic analysis, entity extraction, name matching, and name translation to swiftly and accurately mine unstructured data. Rosette powers multilingual search, government intelligence, e-discovery, and financial compliance. Our research pioneers better, faster, and cheaper techniques to extract forensic evidence, keeping government and law enforcement ahead of the exponential growth of data storage volumes.
Over 250 major organizations, including Amazon.com, EMC, Google, Microsoft, Endeca, Exalead/Dassault, Fujitsu, Hewlett-Packard, Oracle, and many U.S. and foreign governments use our products and services. Learn more at .
Basis Technology Corp.
Tel: +1-617-386-2050
Themen in dieser Pressemitteilung:
Unternehmensinformation / Kurzprofil:
Datum: 04.10.2011 - 08:00 Uhr
Sprache: Deutsch
News-ID 1042334
Anzahl Zeichen: 0
contact information:
Contact person:
Town:
CAMBRIDGE, MA
Phone:
Kategorie:
Internet
Anmerkungen:
Diese Pressemitteilung wurde bisher 56 mal aufgerufen.
Die Pressemitteilung mit dem Titel:
"Basis Technology's Natural Language Processing Software for Search Applications Adds 13 Languages
"
steht unter der journalistisch-redaktionellen Verantwortung von
Basis Technology (Nachricht senden)
Beachten Sie bitte die weiteren Informationen zum Haftungsauschluß (gemäß TMG - TeleMedianGesetz) und dem Datenschutz (gemäß der DSGVO).
