SeVeN: Augmenting Word Embeddings with Unsupervised Relation Vectors

TL;DR

SeVeN introduces a novel approach to encode word relationships as vectors in a continuous space, enhancing semantic understanding beyond traditional word embeddings, and demonstrates improvements in word similarity and text categorization tasks.

Contribution

The paper presents a new method for learning relation vectors using an autoencoder, creating a hybrid semantic network that captures relational information complementing word embeddings.

Findings

Relation vectors capture abstract relational similarities.

Explicit encoding improves word similarity measurement.

Enhances neural text categorization performance.

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.