» What

X-Link is a configurable, Linked Data-based, Named Entity Extraction tool.

» Features top

X-Link is capable to:

  • identify entities of interests (e.g., persons, locations, organizations, etc.) in any type of document
  • link the identified entities with semantic resources (i.e., with URIs)
  • enrich the identified entities with semantic information (i.e., with properties and related entities)
  • infer whether and how the identified entities are associated

The main strength of X-Link is its extensive configurability: the user/administrator/developer can define and update the categories of entities that are interesting for the application at hand by exploiting one or more (on-line) Semantic Knowledge Bases. The user is also able to specify how to link the identified entities with semantic resources and how to enrich them with more information.

This enhanced configurability allows X-Link to be configured for different contexts, for building domain-specific applications (e.g., for identifying drugs in a medical search system, for annotating and exploring fish species in a marine-related web page, etc.).

X-Link can also be dynamically configured through its API (e.g., for supporting a new category of entities or for specifying a new Knowledge Base) even while a corresponding service is running, without requiring to redeploy the underlying application.

X-Link supports the Open NEE Model (Open Annotation Extension) and the Open NEE Configuration Model.

» How to cite X-Link top

Please check the related publications

» Releases top

Please contact for the source package. X-Link is licensed under European Union Public Licence (EUPL). Other licenses can be used on request. Please contact for more information.

» Demos & Applications top
Demos
Applications using X-Link
  • X-Search: Semantic post-processing of the results of keyword search queries

    X-Link is currently used by the X-Search system in two different contexts: in the marine domain (in the context of the iMarine project) and in Patent Search (in the context of the PerFedPat project). X-Search is a meta-search engine that reads the description of an underlying search source, queries that source, analyzes the returned results in various ways and also exploits the availability of semantic repositories. For instance, in iMarine, X-Link has been configured to identify Fish Species, Water Areas, Countries and Regional Fisheries Bodies, while the Knowledge Base that is exploited is the MarineTLO-based Warehouse.

    Try X-Search here.

» Publications top
P. Fafalios, M. Baritakis and Y. Tzitzikas
Exploiting Linked Data for Open and Configurable Named Entity Extraction,
International Journal on Artificial Intelligence Tools, Vol. 24, No. 02 (2015), World Scientific (ISSN: 1793-6349).

Pavlos Fafalios, Manolis Baritakis and Yannis Tzitzikas
Configuring Named Entity Extraction through Real-Time Exploitation of Linked Data
4th International Conference on Web Intelligence, Mining and Semantics (WIMS'14), Thessaloniki, Greece, June 2014.
» Contact / Provide Feedback top
Please contact us by sending an email at tzitzik at ics.forth.gr.
» About top

Institution:
Information System Laboratory (ISL), Institute of Computer Science (ICS),
Foundation for Research and Technology - Hellas (FORTH)

Contact Person:
Yannis Tzitzikas
Email: tzitzik at ics.forth.gr
Personal Web page: http://users.ics.forth.gr/~tzitzik/


Acknowledgements:
This work was partially supported by:
iMarine: Data e-Infrastructure Initiative for Fisheries Management and Conservation of Marine Living Resources Multilingual and Multifaceted Interactive Information Access (MUMIA)

Institute of Computer Science - Foundation for Research and Technology - Hellas
 
 
Terms of Use  |   Privacy Policy