WordNet2Vec: Corpora Agnostic Word Vectorization Method

TL;DR

WordNet2Vec is a novel method that transforms WordNet's complex network into word vectors capturing semantic roles, enabling effective text analysis tasks like sentiment classification across languages.

Contribution

The paper introduces WordNet2Vec, a language-agnostic vectorization technique based on WordNet's network structure, enhancing natural language processing applications.

Findings

Effective sentiment analysis on Amazon dataset

Language-agnostic word vectors capture semantic context

Applicable to various NLP tasks like classification and clustering

Abstract

A complex nature of big data resources demands new methods for structuring especially for textual content. WordNet is a good knowledge source for comprehensive abstraction of natural language as its good implementations exist for many languages. Since WordNet embeds natural language in the form of a complex network, a transformation mechanism WordNet2Vec is proposed in the paper. It creates vectors for each word from WordNet. These vectors encapsulate general position - role of a given word towards all other words in the natural language. Any list or set of such vectors contains knowledge about the context of its component within the whole language. Such word representation can be easily applied to many analytic tasks like classification or clustering. The usefulness of the WordNet2Vec method was demonstrated in sentiment analysis, i.e. classification with transfer learning for the real Amazon opinion textual dataset.