SeVeN: Augmenting word embeddings with unsupervised relation vectors

Espinosa-Anke, Luis ORCID: https://orcid.org/0000-0001-6830-9176 and Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 2018. SeVeN: Augmenting word embeddings with unsupervised relation vectors. Presented at: 27th International Conference on Computational Linguistics (COLING 2018), Santa Fe, NM, USA, 20-26 August 2018.

Preview

PDF - Accepted Post-Print Version Available under License Creative Commons Attribution. Download (225kB) | Preview

Abstract

We present SeVeN (Semantic Vector Networks), a hybrid resource that encodes relationships between words in the form of a graph. Different from traditional semantic networks, these relations are represented as vectors in a continuous vector space. We propose a simple pipeline for learning such relation vectors, which is based on word vector averaging in combination with an ad hoc autoencoder. We show that by explicitly encoding relational information in a dedicated vector space we can capture aspects of word meaning that are complementary to what is captured by word embeddings. For example, by examining clusters of relation vectors, we observe that relational similarities can be identified at a more abstract level than with traditional word vector differences. Finally, we test the effectiveness of semantic vector networks in two tasks: measuring word similarity and neural text categorization. SeVeN is available at bitbucket.org/luisespinosa/seven.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Completion
Status:	Unpublished
Schools:	Computer Science & Informatics
Date of First Compliant Deposit:	18 July 2018
Last Modified:	23 Oct 2022 14:04
URI:	https://orca.cardiff.ac.uk/id/eprint/112683

Citation Data

Cited 13 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item