CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information

02/01/2019
by   Shikhar Vashishth, et al.
0

Open Information Extraction (OpenIE) methods extract (noun phrase, relation phrase, noun phrase) triples from text, resulting in the construction of large Open Knowledge Bases (Open KBs). The noun phrases (NPs) and relation phrases in such Open KBs are not canonicalized, leading to the storage of redundant and ambiguous facts. Recent research has posed canonicalization of Open KBs as clustering over manuallydefined feature spaces. Manual feature engineering is expensive and often sub-optimal. In order to overcome this challenge, we propose Canonicalization using Embeddings and Side Information (CESI) - a novel approach which performs canonicalization over learned embeddings of Open KBs. CESI extends recent advances in KB embedding by incorporating relevant NP and relation phrase side information in a principled manner. Through extensive experiments on multiple real-world datasets, we demonstrate CESI's effectiveness.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/22/2022

Multi-View Clustering for Open Knowledge Base Canonicalization

Open information extraction (OIE) methods extract plenty of OIE triples ...
research
06/17/2020

Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network

Noun phrases and relational phrases in Open Knowledge Bases are often no...
research
12/08/2020

Joint Entity and Relation Canonicalization in Open Knowledge Graphs using Variational Autoencoders

Noun phrases and relation phrases in open knowledge graphs are not canon...
research
12/02/2022

Joint Open Knowledge Base Canonicalization and Linking

Open Information Extraction (OIE) methods extract a large number of OIE ...
research
02/08/2023

COMBO: A Complete Benchmark for Open KG Canonicalization

Open knowledge graph (KG) consists of (subject, relation, object) triple...
research
07/10/2016

Open Information Extraction

Open Information Extraction (Open IE) systems aim to obtain relation tup...
research
11/22/2017

Conditional Image-Text Embedding Networks

This paper presents an approach for grounding phrases in images which jo...

Please sign up or login with your details

Forgot password? Click here to reset