Xapien supports over 200 languages through AI-powered translation technologies. This ensures you can access in-depth, high-quality research globally, no matter where a subject is located or what language they speak.
There are no restrictions on search language - you can enter subject names and identifying details in multiple languages, for instance: "Oleg Deripaska" or "Олег Дерипаска."
You can also enter your subject's name in its native script. For people mostly covered in local-language media, this often pulls in more current sources.
Automatic foreign language content collection
Xapien automatically searches for and collects relevant non-English content alongside existing English search strategies. You do not need to do anything differently - this happens automatically for every report.
When generating a report, Xapien will:
Identify the most relevant language(s) for the subject based on their location, nationality, and associated organisations.
Generate native-language search strategies to uncover content that English-only searches would miss.
Use native-script names where available (e.g. Cyrillic, Chinese, Arabic) to broaden the search.
All of this runs alongside existing English-language collection, so your reports now draw from a significantly wider evidence base.
Why this matters
Important risk signals are often published only in local-language media. Previously, reports relied on English key terms, which meant these signals could be missed. With automatic foreign language collection, Xapien surfaces relevant content from international sources that would not appear in an English-only search.
Also Known As (AKA) enhancements
Alongside foreign language collection, Xapien uses a stable and evidence-backed alias framework for both people and organisations. This includes:
Historical names (e.g. maiden names, former company names)
Trading names
Transliterations (e.g. different Romanisations of the same name)
Native-script forms
Verified name variants are preserved more systematically, which improves the consistency of report outputs and reduces the chance of missing content published under a different name variant.
Things to note
Source cards are translated for you. The title, description and extracts on a non-English source card are shown in English, with a toggle to switch back to the original language. A small number of sources can't be translated and are shown in the original.
Names in the Related Entities section may appear in native script more often as a result of increased foreign-language collection. Where a name is better known in its native script, that's the form you'll see.
If you have feedback on foreign language results in your reports, please reach out to Customer Success or use the Help widget to contact support.