CEF Named-entity recognition

Named-entity recognition (NER) is a tool that aims to identify (people, places and things...) in a text.

You can submit your document and get a list of the people, places or things that are mentioned in it.

This can be useful in many information processing tasks - for example, you could scrape the web and do keyword searches to find all the pages that mention "Ursula von der Leyen" in researching the EU, or perhaps, if you have a taste for controversy, "Donald Trump". This can be useful in monitoring media interest in individuals or places that are currently in the news. For machine translation, it can be used to identify individuals or places and ensure that the official or preferred translations are used.

This system will generate a marked-up list - what you then do with it is limited only by your imagination!

The CEF named-entity recognition service expects a 64 base-encoded file as input and returns a tagged xml file as output.

The CEF Named-entity recognition web service is asynchronous. This means that the client sends a NER request and is notified once the document has been processed. In this way, calling the web service does not block the client. However, the client needs to expose a callback URL which will receive a notification that the named-entity extraction has been completed. The NER web service sends the tagged xml file to the destination URL specified by the client.

The interaction is as follows:

  1. The client sends a NER request to the NER web service;
  2. The NER web service replies synchronously with the request ID (positive number) or an error code (negative number) and an error message;
  3. The NER web service processes the document;
  4. The output is sent back to the callback URL.

The above approach decouples the client from the NER server. It is the responsibility of the Client to submit the initial request, and to react to the callback from the NER server. The request ID returened can be used to correlate the original request with the callback it refers to.

To obtain the credentials needed to access the service:

 

 

Language Coverage
Bulgarian (Cyrillic), Czech (Latin), Croatian (Latin), Danish (Latin), Dutch; Flemish (Latin), English (Latin), Estonian (Latin), Finnish (Latin), French (Latin), German (Latin), Hungarian (Latin), Irish (Latin), Italian (Latin), Latvian (Latin), Lithuanian (Latin), Maltese (Latin), Modern Greek (1453-) (Greek), Polish (Latin), Portuguese (Latin), Romanian; Moldavian; Moldovan (Latin), Slovak (Latin), Slovenian (Latin), Spanish; Castilian (Latin), Swedish (Latin), Norwegian (Latin), Icelandic (Latin), Russian (Cyrillic), Chinese , Turkish
Related Services

Service desk for machine translation

Target Users
  • Public administrations

    National public administrations in the EU Member States, Iceland and Norway

  • EU staff members
Get Started with the service

: Free of charge

Support

Helpdesk:

Interaction Language: English (Latin)

Access the service

Request - Web Service : https://language-tools.ec.europa.eu/NamedEntitiesWS/askNER

Web Service
Input Output
Media Type
Data format HTML , MS-Excel xls , MS-Excel xlsx , MS-Word doc , MS-Word docx , PDF , RTF , Text , XML XML
Data format (other) odt, ods, odp, odg, ott, ots, otp, otg, ppt, ppts
The Catalogue of Services is maintained by the Service Desk of the CEF Automated Translation Platform. The service desk is funded via a contract (SMART 2016/0103) of the EU’s Connecting Europe Facility (CEF) programme.