Confidence-Aware Embedding for Knowledge Graph Entity Typing

Complexity 2021:1-8 (2021)
  Copy   BIBTEX

Abstract

Knowledge graphs entity typing aims to predict the potential types to an entity, that is,. Recently, several embedding models are proposed for KG entity types prediction according to the existing typing information of the tuples in KGs. However, most of them unreasonably assume that all existing entity typing instances in KGs are completely correct, which ignore the nonnegligible entity type noises and may lead to potential errors for the downstream tasks. To address this problem, we propose ConfE, a novel confidence-aware embedding approach for modeling the tuples, which takes tuple confidence into consideration for learning better embeddings. Specifically, we learn the embeddings of entities and entity types in separate entity space and entity type space since they are different objects in KGs. We utilize an asymmetric matrix to specify the interaction of their embeddings and incorporate the tuple confidence as well. To make the tuple confidence more universal, we consider only the internal structural information in existing KGs. We evaluate our model on two tasks, including entity type noise detection and entity type prediction. The extensive experimental results in two public benchmark datasets demonstrate that our proposed model outperforms all baselines on all tasks, which verify the effectiveness of ConfE in learning better embeddings on noisy KGs. The source code and data of this work can be obtained from https://github.com/swufenlp/ConfE.

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 90,616

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Concrete Entities and Concrete Relations.Panayot Butchvarov - 1957 - Review of Metaphysics 10 (3):412 - 422.
An ontology of weak entity realism for HPC kinds.Reuben Sass - 2021 - Synthese 198 (12):11861-11880.
Could Theoretical Entities Save Realism?Mohamed Elsamahi - 1994 - PSA: Proceedings of the Biennial Meeting of the Philosophy of Science Association 1994:173-180.
Haecceity. [REVIEW]Ramom M. Lemos - 1995 - Review of Metaphysics 48 (4):928-929.
The Questioning Turing Test.Nicola Damassino - 2020 - Minds and Machines 30 (4):563-587.
Reference, Success and Entity Realism.Howard Sankey - 2012 - Kairos. Revista de Filosofia and Ciência 5:31-42.

Analytics

Added to PP
2021-04-17

Downloads
4 (#1,426,706)

6 months
3 (#447,120)

Historical graph of downloads
How can I increase my downloads?

Author Profiles

References found in this work

No references found.

Add more references