(Newswire Today) —  London, United Kingdom, 2007-02-15 - Text mining, which is said to be about making human language understandable for computers, encounters the challenge of a multilingual and multicultured European population.

“Text analytics is about making human communications comprehensible to computers” comments Seth Grimes, President of Alta Plana. There is no disputing this fact, and the challenge of achieving this goal is made all the more difficult in the multi-lingual, multi-cultural landscape that is Europe. So what kind of obstacles are text analytics experts up against in a territory as heavily populated with difference in language, dialect and idioms as Europe?

The need for text mining technology in Europe that can process 25 different languages and a multitude of dialects is a complicated necessity only the most dedicated could rise to. The question is, does this myriad of languages and dialects across Europe create an opportunity for TA developers… or a potential headache?

“It definitely creates opportunities," says Anton Heijs, CTO at Treparel, "There are different approaches in text mining / text analytics; from rule based approaches where many rules are needed for good accuracy, from on the hand detailed classification to on the other hand the natural language based approaches where knowledge of language specifics are used to obtain good results; for the latter a lot of language knowledge is required in the first I instance”. Anjon Hejis will explore this topic at greater length alongside Philips at the inaugural European Text Analytics Summit on April 26th and 27th at Amsterdam.

So how do opportunities in Europe differ from those in the United States? "The business environment in Europe is much more "international" and crosses many more cultures, and languages.” says Randy Collica, Sr Data Analyst at HP says. He continues, "In America, although more cultures and languages are needed, the basic business still is almost exclusively English or perhaps Spanish in some areas”

“It is the new ROI: the return of Information; companies that take advantage of their unstructured data are much better informed when taking major decisions” says Belén Gallego, Summit Director of the European Text Analytics Summit. “European Solution Providers and end users need to gather under the same roof to move the unstructured data space forward - it is the only way to ensure that the tools provided are easily deployable and provide a high return for investment – which is exactly what the European Text Analytics Summit aims at doing”

Lexis Nexis, SPSS, Temis, Vivisimo, Linguamatics, ISYS Search, Treparel and Infolutions are the kind of companies spearheading text analytics initiatives across Europe. All are set to meet in Amsterdam on April 26th and 27th to discuss new technologies and techniques that allow clients to extract the maximum value from unstructured data including Multilingual Technologies, Business Deployments and Text Analytic in CRM and patent discovery.

Agency / Source: