SeVeN: Augmenting Word Embeddings with Unsupervised Relation Vectors

08/18/2018
by   Luis Espinosa-Anke, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/17/2019

Analyzing Structures in the Semantic Vector Space: A Framework for Decomposing Word Embeddings

Word embeddings are rich word representations, which in combination with...
research
01/20/2016

Semantic Word Clusters Using Signed Normalized Graph Cuts

Vector space representations of words capture many aspects of word simil...
research
10/11/2018

Towards Understanding Linear Word Analogies

A surprising property of word vectors is that vector algebra can often b...
research
07/22/2011

Analogy perception applied to seven tests of word comprehension

It has been argued that analogy is the core of cognition. In AI research...
research
03/05/2017

Random vector generation of a semantic space

We show how random vectors and random projection can be implemented in t...
research
09/05/2018

Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell

This paper presents an approach for investigating the nature of semantic...
research
09/16/2013

Domain and Function: A Dual-Space Model of Semantic Relations and Compositions

Given appropriate representations of the semantic relations between carp...

Please sign up or login with your details

Forgot password? Click here to reset