Enhancing Semantic Word Representations by Embedding Deeper Word Relationships

TL;DR

This paper introduces an enhanced word embedding method that combines context-based statistics, deeper relationships from ConceptNet, and visualization techniques, significantly improving semantic similarity measures in NLU tasks.

Contribution

It presents a novel word embedding approach integrating analogy, context, and deeper relationships, fine-tuned with Self-Organizing Map, outperforming existing methods and surpassing human performance.

Findings

Achieved a Spearman correlation of 0.886 on Simlex 999

Outperformed current state-of-the-art methods

Exceeded human performance in semantic similarity tasks

Abstract

Word representations are created using analogy context-based statistics and lexical relations on words. Word representations are inputs for the learning models in Natural Language Understanding (NLU) tasks. However, to understand language, knowing only the context is not sufficient. Reading between the lines is a key component of NLU. Embedding deeper word relationships which are not represented in the context enhances the word representation. This paper presents a word embedding which combines an analogy, context-based statistics using Word2Vec, and deeper word relationships using Conceptnet, to create an expanded word representation. In order to fine-tune the word representation, Self-Organizing Map is used to optimize it. The proposed word representation is compared with semantic word representations using Simlex 999. Furthermore, the use of 3D visual representations has shown to be capable of representing the similarity and association between words. The proposed word representation shows a Spearman correlation score of 0.886 and provided the best results when compared to the current state-of-the-art methods, and exceed the human performance of 0.78.