Create a Semantic Fingerprint for any text and view its related contexts in all available languages.
Semantically aligned semantic spaces allow for seamless cross-language operations. The Cross-Lingual Topic Analyzer demonstrates that the Cortical.io Retina understands the meaning of text, independently of the language used.
To get started, just input a text in one of the available languages: you will retrieve terms related to the topic of the text in all available languages.
You can use this technology to extract cross-language meta-data, for example using English keywords to extract meta-data from Spanish websites. If you have created a filter for specific topics in news feeds or tweets, you can also use this tool to verify that the same topics in other languages will be appropriately filtered.
The Cross-Lingual Topic Analyzer uses the underlying Cortical.io Retina Languages API to first detect the language of the input text. A semantic fingerprint of the input text is then generated using the corresponding language Retina. In the final step, the generated semantic fingerprint is used to retrieve a list of similar terms related to the input text for each of the available languages.