Traversing Knowledge Graphs in Vector Space

06/03/2015
by   Kelvin Guu, et al.
0

Path queries on a knowledge graph can be used to answer compositional questions such as "What languages are spoken by people living in Lisbon?". However, knowledge graphs often have missing facts (edges) which disrupts path queries. Recent models for knowledge base completion impute missing facts by embedding knowledge graphs in vector spaces. We show that these models can be recursively applied to answer path queries, but that they suffer from cascading errors. This motivates a new "compositional" training objective, which dramatically improves all models' ability to answer path queries, in some cases more than doubling accuracy. On a standard knowledge base completion task, we also demonstrate that compositional training acts as a novel form of structural regularization, reliably improving performance across all base models (reducing errors by up to 43

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/17/2018

On Evaluating Embedding Models for Knowledge Base Completion

Knowledge bases contribute to many artificial intelligence tasks, yet th...
research
12/07/2016

Knowledge Representation in Graphs using Convolutional Neural Networks

Knowledge Graphs (KG) constitute a flexible representation of complex re...
research
05/17/2018

Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures

Embedding methods which enforce a partial order or lattice structure ove...
research
04/24/2015

Compositional Vector Space Models for Knowledge Base Completion

Knowledge base (KB) completion adds new facts to a KB by making inferenc...
research
06/13/2016

Using a Distributional Semantic Vector Space with a Knowledge Base for Reasoning in Uncertain Conditions

The inherent inflexibility and incompleteness of commonsense knowledge b...
research
11/14/2016

Traversing Knowledge Graph in Vector Space without Symbolic Space Guidance

Recent studies on knowledge base completion, the task of recovering miss...
research
11/02/2018

Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations

Neural models of Knowledge Base data have typically employed composition...

Please sign up or login with your details

Forgot password? Click here to reset