Towards Exploiting Implicit Human Feedback for Improving RDF2vec Embeddings

RDF2vec is a technique for creating vector space embeddings from an RDF knowledge graph, i.e., representing each entity in the graph as a vector. It first creates sequences of nodes by performing random walks on the graph. In a second step, those sequences are processed by the word2vec algorithm for...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-04
Main Authors: Ahmad Al Taweel, Paulheim, Heiko
Format: Article
Language:English
Subjects:
Algorithms
Feedback
Graphical representations
Knowledge representation
Markov analysis
Random walk
Transition probabilities
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:RDF2vec is a technique for creating vector space embeddings from an RDF knowledge graph, i.e., representing each entity in the graph as a vector. It first creates sequences of nodes by performing random walks on the graph. In a second step, those sequences are processed by the word2vec algorithm for creating the actual embeddings. In this paper, we explore the use of external edge weights for guiding the random walks. As edge weights, transition probabilities between pages in Wikipedia are used as a proxy for the human feedback for the importance of an edge. We show that in some scenarios, RDF2vec utilizing those transition probabilities can outperform both RDF2vec based on random walks as well as the usage of graph internal edge weights.
ISSN:2331-8422