ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Care: Open knowledge graph embeddings

Gupta, S and Kenkre, S and Talukdar, P (2020) Care: Open knowledge graph embeddings. In: 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, 3-7 November 2019, Hong Kong; China, pp. 378-388.

[img] PDF
CON_EMP_MET_NAT_LAN_PRO_378-388_2019.pdf - Published Version
Restricted to Registered users only

Download (834kB) | Request a copy
Official URL: https://dx.doi.org/10.18653/v1/D19-1036

Abstract

Open Information Extraction (OpenIE) methods are effective at extracting (noun phrase, relation phrase, noun phrase) triples from text, e.g., (Barack Obama, took birth in, Honolulu). Organization of such triples in the form of a graph with noun phrases (NPs) as nodes and relation phrases (RPs) as edges results in the construction of Open Knowledge Graphs (OpenKGs). In order to use such OpenKGs in downstream tasks, it is often desirable to learn embeddings of the NPs and RPs present in the graph. Even though several Knowledge Graph (KG) embedding methods have been recently proposed, all of those methods have targeted Ontological KGs, as opposed to OpenKGs. Straightforward application of existing Ontological KG embedding methods to OpenKGs is challenging, as unlike Ontological KGs, OpenKGs are not canonicalized, i.e., a real-world entity may be represented using multiple nodes in the OpenKG, with each node corresponding to a different NP referring to the entity. For example, nodes with labels Barack Obama, Obama, and President Obama may refer to the same real-world entity Barack Obama. Even though canonicalization of OpenKGs has received some attention lately, output of such methods has not been used to improve OpenKG embeddings. We fill this gap in the paper and propose Canonicalization-infused Representations (CaRe) for OpenKGs. Through extensive experiments, we observe that CaRe enables existing models to adapt to the challenges in OpenKGs and achieve substantial improvements for the link prediction task. © 2019 Association for Computational Linguistics

Item Type: Conference Paper
Additional Information: cited By 0; Conference of 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019 ; Conference Date: 3 November 2019 Through 7 November 2019; Conference Code:159367
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Depositing User: Id for Latest eprints
Date Deposited: 15 Oct 2020 09:43
Last Modified: 15 Oct 2020 09:43
URI: http://eprints.iisc.ac.in/id/eprint/65509

Actions (login required)

View Item View Item