IDEL: In-Database Neural Entity Linking

We present a novel architecture In-Database Entity Linking (IDEL), in which we integrate the analytical RDBMS MonetDB with neural text mining abilities. To the best of our knowledge, this is the first defacto implemented system integrating entity-linking in a database. IDEL represents text and relat...

Full description

Saved in:
Bibliographic Details
Main Authors: Kilias, Torsten, Loser, Alexander, Gers, Felix, Zhang, Ying, Koopmanschap, Richard, Kersten, Martin
Format: Conference Proceeding
Language:English
Subjects:
Computer architecture
Entity Linking
In-Database Machine Learning
Joining processes
Joint Embedding Space
Machine learning
Neural networks
Pairwise Contrastive Ranking Loss
Structured Query Language
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a novel architecture In-Database Entity Linking (IDEL), in which we integrate the analytical RDBMS MonetDB with neural text mining abilities. To the best of our knowledge, this is the first defacto implemented system integrating entity-linking in a database. IDEL represents text and relational data in a joint vector space with neural embeddings and can compensate errors with ambiguous entity representations. To detect matching entities, we propose a novel similarity function based on joint neural embeddings which are learned via minimizing pairwise contrastive ranking loss. This function utilizes high dimensional index structures for fast retrieval of matching entities. The system achieves zero cost for data shipping and transformation by utilizing MonetDB's ability to embed Python processes in its kernel and exchange data in NumPy arrays. We report from experiments on the WebNLG corpus on ten entity types high F-measures and low execution times.
ISSN:2375-9356
DOI:10.1109/BIGCOMP.2019.8679486