About

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.

Benchmarks

No evaluation results yet. Help compare methods by submit evaluation metrics.

Greatest papers with code

Fast Linear Model for Knowledge Graph Embeddings

30 Oct 2017facebookresearch/fastText

This paper shows that a simple baseline based on a Bag-of-Words (BoW) representation learns surprisingly good knowledge graph embeddings.

KNOWLEDGE BASE COMPLETION KNOWLEDGE GRAPH EMBEDDINGS QUESTION ANSWERING

Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs

ACL 2019 deepakn97/relationPrediction

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).

 Ranked #1 on Knowledge Graph Completion on FB15k-237 (Hits@1 metric)

KNOWLEDGE BASE COMPLETION KNOWLEDGE GRAPH COMPLETION KNOWLEDGE GRAPH EMBEDDINGS LINK PREDICTION

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

23 Mar 2017Sujit-O/pykg2vec

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

KNOWLEDGE BASE COMPLETION KNOWLEDGE GRAPH COMPLETION LINK PREDICTION

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

2 Jun 2015glorotxa/SME

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

KNOWLEDGE BASE COMPLETION LINK PREDICTION

KBGAN: Adversarial Learning for Knowledge Graph Embeddings

NAACL 2018 cai-lw/KBGAN

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.

KNOWLEDGE BASE COMPLETION KNOWLEDGE GRAPH EMBEDDING KNOWLEDGE GRAPH EMBEDDINGS KNOWLEDGE GRAPHS LINK PREDICTION

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

14 Sep 2017nle-ml/mmkb

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

KNOWLEDGE BASE COMPLETION REPRESENTATION LEARNING

Canonical Tensor Decomposition for Knowledge Base Completion

ICML 2018 facebookresearch/kbc

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

KNOWLEDGE BASE COMPLETION LINK PREDICTION TENSOR DECOMPOSITION

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

NAACL 2018 daiquocnguyen/ConvKB

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

KNOWLEDGE BASE COMPLETION LINK PREDICTION