Two things can make a difference in your products which deal with text: semantics and multilinguality. Comprehendo enables both by providing a system which understands text by associating explicit meanings with words, multiword expressions and phrases. Such meanings come from WordAtlas and are multilingual by design.

Comprehendo is based on state-of-the-art Word Sense Disambiguation and Entity Linking and can be applied to any language and text genre on a large scale. As a result, users can process large amounts of texts, articles, blogs, posts, etc. in multiple languages and aggregate this information in any way they like (for instance, using Extraggo for text analytics).

Comprehendo works both with standard text (sentences, paragraphs, documents, etc.), and text snippets (such as tags, word clouds, user queries, etc.) and brings two main advantages:

• It enables the semantic aggregation of similar information written using different words, either in the same language, or in different languages (for instance, what is the world talking about today in different language newspapers?)

• It enables discrimination between different uses of the same word (for example, users searching for oil might be interested in fuel or in food depending on contextual cue words

It works with full text, but also snippets or query logs, among others. 

Comprehendo is not a translator: it understands text and associates concepts and named entities with words and phrases. Such concepts and entities are provided by WordAtlas, the Babelscape multilingual knowledge graph, which makes it possible to scale to arbitrary languages at any time.