Knowledge Base Completion

53 papers with code • 0 benchmarks • 1 datasets

Knowledge base completion is the task which automatically infers missing facts by reasoning about the information already present in the knowledge base. A knowledge base is a collection of relational facts, often represented in the form of "subject", "relation", "object"-triples.


Most implemented papers

Modeling Relational Data with Graph Convolutional Networks

tkipf/relational-gcn 17 Mar 2017

We demonstrate the effectiveness of R-GCNs as a stand-alone model for entity classification.

A survey of embedding models of entities and relationships for knowledge graph completion

Sujit-O/pykg2vec COLING (TextGraphs) 2020

Knowledge graphs (KGs) of real-world facts about entities and their relationships are useful resources for a variety of natural language processing tasks.

KBGAN: Adversarial Learning for Knowledge Graph Embeddings

cai-lw/KBGAN NAACL 2018

This framework is independent of the concrete form of generator and discriminator, and therefore can utilize a wide variety of knowledge graph embedding models as its building blocks.

A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network

daiquocnguyen/ConvKB NAACL 2018

This 3-column matrix is then fed to a convolution layer where multiple filters are operated on the matrix to generate different feature maps.

Canonical Tensor Decomposition for Knowledge Base Completion

facebookresearch/kbc ICML 2018

The problem of Knowledge Base Completion can be framed as a 3rd-order binary tensor completion problem.

Combining Two And Three-Way Embeddings Models for Link Prediction in Knowledge Bases

glorotxa/SME 2 Jun 2015

This paper tackles the problem of endogenous link prediction for Knowledge Base completion.

Joint Matrix-Tensor Factorization for Knowledge Base Inference

dair-iitd/kbi 2 Jun 2017

If not, what characteristics of a dataset determine the performance of MF and TF models?

KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features

nle-ml/mmkb 14 Sep 2017

We present KBLRN, a framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features.

Embedding Multimodal Relational Data for Knowledge Base Completion

pouyapez/mkbe EMNLP 2018

In this paper, we propose multimodal knowledge base embeddings (MKBE) that use different neural encoders for this variety of observed data, and combine them with existing relational models to learn embeddings of the entities and multimodal data.

Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs

deepakn97/relationPrediction ACL 2019

The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion (also known as relation prediction).