Turning Information
... into Knowledge
Our Solutions Semantic Technologies Support Partners About
Cross-lingual Similarity search Linguistic database Installation time Training/Support Sources and formats Volume/Performance Security and privacy System environment Informational standards USPs/demo version
Contact English Deutsch Franšais


What does "cross-language search" mean?

Some search engine providers claim to support multiple languages if they can handle and index documents written in different languages. They search for the exact appearance of the entered search terms; e.g. "war" finds English documents referring to military actions but also finds German documents containing "war" in the sense of "was" (i.e. a meaningless glue word). This is sometimes called multilingual or multi-language search and is different from cross-language search.

A true cross-language search is possible only if the search engine is able to recognize the thematic content of a document, i.e. if the system realizes that the English translation of a French (or a German, etc.) document is equivalent to the original document. This advanced technique is a key feature of InfoCodex. It simultaneously finds documents in all supported languages, without the need for a cumbersome (and often arbitrary) translation into each language. Because of the cross-language content recognition and a well-founded similarity measure, the documents can be ordered by their relevance to the search query.


26. - 27.09.2016 Keynote at Big Data Analytics and Data Mining, London

14.03.16 WebPlatform Ares4 with InfoCodex presented at CeBIT 2016 Hannover

16.09.15 Presentation at SEMANTICS Vienna 2015 "Scientific Discovery by Machine ..." (Session 1.4)

02.06.2015 Presentation at Swiss Competitive Intelligence

26.02.13 Semantic Tech Turns up Biomarkers

13.02.13 Discovery of Novel Biomarkers (joint paper with Merck & Co)