evidoria

← Back to browse

Good practice Imported

data.europa.eu's eTranslation — Automated Neural Machine Translation of Open-Data Metadata Across 24 EU Languages

Luxembourg · Luxembourg City · See the Luxembourg profile

The EU's open-data portal auto-translates harvested dataset metadata into all 24 official EU languages via the Commission's eTranslation engine — fully automated, covering 1.6M+ datasets from 178 catalogues — though the portal warns translations may be imperfect.

data.europa.eu's eTranslation — Automated Neural Machine Translation of Open-Data Metadata Across 24 EU Languages

Details

Promoter
Publications Office of the European Union
Period
2015–present
Keywords
open data, machine translation, metadata, multilingual government data

Description

The Publications Office of the European Union runs data.europa.eu, the EU's central open-data portal, which harvests metadata from 178 national, regional and EU-institutional data catalogues and currently indexes over 1.6 million datasets.
To make that catalogue usable across the Union's 24 official languages, the portal automatically translates harvested dataset titles and descriptions using eTranslation, the European Commission's standing neural machine-translation service, which the Commission describes as 'fully automated and involv[ing] no human intervention.' eTranslation is also used across many other EU digital services, giving this metadata-translation use a track record of reuse beyond a single pilot.
The current version of the portal launched on 21 April 2021, building on a beta version that had run since November 2015 — a continuity of nearly a decade under the same institutional owner.
Because the translation is machine-generated without human review, the portal displays a warning to users that automated translations may contain errors, and independent academic analysis comparing EU and Gulf open-data portals has specifically flagged machine-translated metadata quality as a limitation worth watching rather than a solved problem — a caveat this entry preserves rather than glossing over.

Read the full analysis: https://commission.europa.eu/languages-our-websites/use-machine-translation-europa_en

Implementation

Implementation detail (cost, timeline, staffing, conditions for success) is not yet available for this practice.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Attachments

Similar practices you may find useful