Rosette Base Linguistics for European Languages“Basis Technology’s Rosette European Language Analyzers have been instrumental in enhancing the multilingual capabilities of our Automated Self-Service Platform, InQuira 6. We selected Basis because of their proven success at offering top-notch linguistic tools for powering information retrieval and strong reputation for superior customer support. Their technology allowed us to quickly make our product available for multiple geographic markets”
— Willie Kim,
Vice President of Product Management,
InQuira
Text mining and information retrieval of European language text is more accurate when documents have gone though a thorough linguistic analysis. Our Rosette Base Linguistics for European languages helps applications overcome many of the challenges that can lead to inaccurate processing, such as the presence of compound nouns (common in German) and contractions such as “l'” in French (as in “l'eau”).
Features:
- Lemmatization and Stemming
• Input: lu Output: lire
• Input: gezogen Output: ziehen - Part of Speech Analysis
• éditeurs —> Plural Noun
• Heiße —> Adjective - Noun Decompounding
• Input: Kontrollsysteme Output: [Kontroll] [systeme]
• Input: Jugendarbeit Output [Jugend] [arbeit] - Context Based Analysis
Base Linguistics for European languages is currently available for Czech, Dutch, French, German, Greek, Hungarian, Italian, Polish, Portuguese, Russian and Spanish, with a number of other under development. Click here for more information on Base Linguistics for English. For more information on upcoming languages, contact us at info@basistech.com.



