Skip to content

Entity Linking powered by Graph Embedding

Thema: Linked Data

Zeit: special 13:30 - 14:00

Raum: 3.50Ort: Welle7, Bern

In this talk, i will present a technique for entity linking that employs graph embeddings to perform collective disambiguation.


Weitere Informationen

Entity Linking (EL), the task of mapping ambiguous Named Entities to unique identifiers in a knowledge base, is a cornerstone of multiple Information Retrieval and Text Analysis systems. In this talk, i will present a technique for entity linking that employs graph embeddings to perform collective disambiguation. We implement and evaluate an EL pipeline that uses DBpedia as knowledge base and leverages specific algorithms for fast candidate search and high-performance state-space search optimization. Compared to existing solutions, our approach offers state-of-the-art accuracy on a variety of datasets without any supervised training and provides real-time execution even when processing documents with dozens of Named Entities.

Paper: https://dl.acm.org/citation.cfm?id=3328499


Zielgruppe

Anyone interested in interlinking data




adrian.gschwend@zazuko.com

 

Speakers

Rhicheek Patra, Oracle Labs

© DINAcon 2019
Konferenz für digitale Nachhaltigkeit
Welle7 Workspace in Bern

Created by WebBee

DINAcon_Logo_web_white_long