About: Relation Induction in Word Embeddings Revisited

Not logged in : Login

(Sponging disallowed)

Facets (new session)
Description
Metadata
Settings
- Rule:
- Inverse Functional Properties:
- "Same As":

About: Relation Induction in Word Embeddings Revisited Goto Sponge NotDistinct Permalink

An Entity of Type : bibo:BookSection, within Data Space : linkeddata.uriburner.com:28898 associated with source document(s)

Attributes	Values
type	http://eprints.org/ontology/BookSectionEPrint http://eprints.org/ontology/EPrint Article Book Section
seeAlso	HTML Summary of #67263 Relation Induction in Word Embeddings Revisited
http://eprints.org/ontology/hasAccepted	Relation Induction in Word Embeddings Revisited (PDF)
http://eprints.org/ontology/hasDocument	Relation Induction in Word Embeddings Revisited (PDF) Relation Induction in Word Embeddings Revisited (Other) Relation Induction in Word Embeddings Revisited (Other) Relation Induction in Word Embeddings Revisited (Other) Relation Induction in Word Embeddings Revisited (Other) Relation Induction in Word Embeddings Revisited (Other)
dc:hasVersion	Relation Induction in Word Embeddings Revisited (PDF)
Title	Relation Induction in Word Embeddings Revisited
described by	https://demo.openlinksw.com/about/id/entity/https/www.cs.kent.ac.uk/people/staff/akj22/materials/CO644/export_kar_RDFN3.n3 https://demo.openlinksw.com/about/id/entity/https/raw.githubusercontent.com/annajordanous/CO644Files/main/export_kar_RDFN3.n3
Date	2018-05-16
Creator	Steven Schockaert Zied Bouraoui Shoaib Jameel
status	peer reviewed published
Publisher	Association for Computational Linguistics
abstract	Given a set of instances of some relation, the relation induction task is to predict which other word pairs are likely to be related in the same way. While it is natural to use word embeddingsfor this task, standard approaches based on vector translations turn out to perform poorly. To address this issue, we propose two probabilistic relation induction models. The first model is based on translations, but uses Gaussians to explicitly model the variability of these translations and to encode soft constraints on the source and target words that may be chosen. In the second model, we use Bayesian linear regression to encode the assumption that there is a linear relationship between the vector representations of related words, which is considerably weaker than the assumption underlying translation based models.
Is Part Of	https://kar.kent.ac.uk/id/repository
list of authors	https://kar.kent.ac.uk/id/eprint/67263#authors
presented at	27th International Conference on Computational Linguistics (COLING 2018)
is topic of	https://www.cs.kent.ac.uk/people/staff/akj22/materials/CO644/export_kar_RDFN3.n3 https://raw.githubusercontent.com/annajordanous/CO644Files/main/export_kar_RDFN3.n3
is primary topic of	HTML Summary of #67263 Relation Induction in Word Embeddings Revisited

Faceted Search & Find service v1.17_git149 as of Dec 03 2024

Alternative Linked Data Documents: iSPARQL | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 08.03.3332 as of Jan 29 2025, on Linux (x86_64-generic-linux-glibc25), Single-Server Edition (378 GB total memory, 22 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2025 OpenLink Software