Lexalytics Announces Availability of Salience in Chinese
Boston, MA (PRWEB) October 23, 2013 -- Lexalytics, a leader in text and sentiment analysis software, is pleased to announce the release of the new Chinese Native Language Pack for their Salience Engine. Chinese is the first character-based written language to be supported by Salience.
Lexalytics is one of the few text analysis companies to offer a native language based approach to foreign language analytics. “Applying sentiment analysis in native Chinese, as opposed to first translating the text to English, gives us much more accurate and nuanced results. By eliminating that middle step, we’re able to catch things that would otherwise have been lost in translation,” explains Ori Sasson, CEO of Simulation Software and Technology (S2T).
The Chinese Native Language Pack includes all the standard Salience tools, redesigned to accomodate the unique structure of the Chinese language. This includes n-grams at the character level, rather than word level, as well as Named Entity Recognition, Text Classification, Sentiment, and everything else needed to identify the “who”, “what”, and “how” that is being discussed. The Chinese language pack currently only supports Mandarin, but does support both Simplified and Traditional characters.
“What made Chinese language support such a great challenge was the way it forced us to think outside the contraints of how our language is structured,” said Seth Redmore, Lexalytics’ VP of Product Management. “ For instance, Chinese doesn’t have any seperation between words the way English and the other languages we’ve worked with so far do. In order to solve this problem we developed composite word support, so that our software could recognize words without needing spaces or other indicators to divide them. That actually opened the doors to analyzing social media hashtags, like “#ilovefood”, which we hadn’t been able to do previously.”
The Salience Engine is the leading text processing engine that provides in-depth text analysis, categorization and classification for over 3 billion documents per day. Chinese is the sixth language to be supported by Salience, following German, Spanish, Portuguese, French, and English.
About Lexalytics
A text mining company founded in 2003, Lexalytics was first with sentiment analysis, first with multi-level sentiment, first with automatic theme detection, first with integrating Wikipedia™ as a knowledge base, and continues to roll out innovation with every release. Lexalytics’ software for text analysis, Salience, is engineered for easy integration into third-party applications, and is a critical component in many high-volume content processing services for industries such as social media monitoring, survey analysis, reputation management, online media, eDiscovery, cyber-intelligence, and more.
Twitter: @lexalytics
About Simulation Software and Technology
Simulation Software & Technology (S2T) Pte Ltd is a systems house based in Singapore. S2T is the leading supplier of text analytics systems in South East Asia for applications in National Security, Law Enforcement, Social Media Monitoring, and Competitive Intelligence. S2T’s GoldenSpear line of products provides customers a single platform where insights can be extracted from both social media and web sources as well as internal sources such as CRM data and internal reports. For more information visit http://www.simulation.com.sg
Press Contact:
Seth Redmore
VP Marketing and Product Management, Lexalytics
@sredmore
1-800-377-8036 x2
sredmore(at)lexalytics(dot)com
Seth Redmore, Lexalytics, http://www.lexalytics.com, 1-800-377-8036 x2, [email protected]
Share this article