knowledge-graph-completion

Triple Classification

3260 papers • 126 benchmarks • 313 datasets

Triple classification aims to judge whether a given triple (h, r, t) is correct or not with respect to the knowledge graph.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in knowledge-graph-completion

Trend

Dataset

Best Model

Actions

YAGO39K

Libraries

i

Use these libraries to find knowledge-graph-completion models and implementations

Datasets

Subtasks

Knowledge Graph Embeddings

Most implemented papers

Learning Entity and Relation Embeddings for Knowledge Graph Completion

Zhiyuan Liu, Yankai Lin, Maosong Sun, Xuan Zhu, Yang Liu•Sat Jan 24 2015

TransR is proposed to build entity and relation embeddings in separate entity space and relation spaces by first projecting entities from entity space to corresponding relation space and then building translations between projected entities.

3847

Content

0

Paper Graph

KG-BERT: BERT for Knowledge Graph Completion

Liang Yao, Chengsheng Mao, Yuan Luo•Fri Sep 06 2019

This work treats triples in knowledge graphs as textual sequences and proposes a novel framework named Knowledge Graph Bidirectional Encoder Representations from Transformer (KG-BERT) to model these triples.

736 0

Paper Graph

Knowledge Representation Learning: A Quantitative Review

Xu Han, Zhiyuan Liu, Yankai Lin, Maosong Sun, Ruobing Xie•Thu Dec 27 2018

This article extensively conduct and quantitative comparison and analysis of several typical KRL methods on three evaluation tasks of knowledge acquisition including knowledge graph completion, triple classification, and relation extraction.

63 0

Paper Graph

Reasoning on Knowledge Graphs with Debate Dynamics

Yunpu Ma, Volker Tresp, Marcel Hildebrandt, Jorge Andres Quintero Serna, Martin Ringsquandl, Mitchell Joblin•Wed Jan 01 2020

The focus of this work is to create an explainable method that maintains a competitive predictive accuracy, and it is found that the method outperforms several baselines on the benchmark datasets FB15k-237, WN18RR, and Hetionet.

58 0

Paper Graph

CoDEx: A Comprehensive Knowledge Graph Completion Benchmark

Tara Safavi, Danai Koutra•Tue Sep 15 2020

CoDEx is distinguished from the popular FB15K-237 knowledge graph completion dataset by showing that CoDEx covers more diverse and interpretable content, and is a more difficult link prediction benchmark.

154 0

Paper Graph

Image-embodied Knowledge Representation Learning

Zhiyuan Liu, Maosong Sun, Ruobing Xie, Huanbo Luan•Wed Sep 21 2016

Experimental results demonstrate that the proposed Image-embodied Knowledge Representation Learning models outperform all baselines on both tasks, which indicates the significance of visual information for knowledge representations and the capability of the models in learning knowledge representations with images.

266 0

Paper Graph

Does William Shakespeare REALLY Write Hamlet? Knowledge Representation Learning with Confidence

Zhiyuan Liu, Maosong Sun, Ruobing Xie•Sun Apr 30 2017

A novel confidence-aware knowledge representation learning framework (CKRL), which detects possible noises in KGs while learning knowledge representations with confidence simultaneously and proposes three kinds of triple confidences considering both local and global structural information.

107 0

Paper Graph

A Relational Memory-based Embedding Model for Triple Classification and Search Personalization

D. Q. Nguyen, T. Nguyen, Dinh Q. Phung•Fri Jul 12 2019

A novel embedding model is introduced that explores a relational memory network to encode potential dependencies in relationship triples and obtains state-of-the-art results on SEARCH17 for the search personalization task, and on WN11 and FB13 for the triple classification task.

24 0

Paper Graph

Differentiating Concepts and Instances for Knowledge Graph Embedding

Zhiyuan Liu, Juan-Zi Li, Lei Hou, Xin Lv•Sun Nov 11 2018

A novel knowledge graph embedding model named TransC is proposed by differentiating concepts and instances by encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space.

99 0

Paper Graph

On the Role of Conceptualization in Commonsense Knowledge Graph Construction

Yuxiao Dong, Yangqiu Song, Kun Xu, Mutian He•Thu Mar 05 2020

This work introduces to CKG construction methods conceptualization, i.e., to view entities mentioned in text as instances of specific concepts or vice versa, and builds synthetic triples by conceptualization.

13 0

Paper Graph

Adding a benchmark result helps the community track progress.