Cross-lingual

Autonomy’s technology uses probabilistic modeling to extract meaning from digital content and forgoes language dependent parsing or dictionaries to form ideas. Because Autonomy treats words merely as abstract symbols of meaning, it is completely language independent. It does not rely on an intimate knowledge of a language’s grammatical structure, but rather derives its understanding through the context of the words’ occurrence rather than through a rigid definition of grammar. This highly mathematical logic yields high accuracy, and performance is further optimized through proprietary stemming algorithms, “sentence breaking” libraries, stoplists and n-grams.

By extracting information from every file processed, IDOL continually learns positive and negative language structures and concepts. Although Autonomy’s fundamentals are predicated on a language independent model, it is still capable of using linguistic analysis to parse semantics to an intra-file level. For instance, the Sentiment Analysis functionality can determine the degree to which a sentiment is positive, negative or neutral for the entire content or a segment of the content. A blogger may have a positive opinion on the iPod, but a negative one on the iPhone, all within the same entry.

Autonomy’s software analyzes units of word and not characters, so it also works well with double byte languages. It supports over 100 languages, including English, German, French, Italian, Chinese and Japanese, and can even be easily configured to auto-detect the language of incoming content.

Autonomy Virage is the only technology on the market which allows for cross-lingual search and data management of video and audio content. For example, an employee based in New York and working in English may need to search foreign multimedia in its native language: the content of Arabic broadcast streams can be searched in English and the content fully understood. This language agnostic approach offers a significant benefit to any international business by enabling colleagues separated not only by miles, but also by language to collaborate and share knowledge.

There is no compromise to the accuracy and concepts extracted regardless of the language used. Autonomy Virage currently supports 25 single and multi-byte languages, through its Audio Analysis Plug-ins. This cross-lingual search facility is invaluable in today’s world.