Can Network Embedding of Distributional Thesaurus be Combined with Word Vectors for Better Representation?

TL;DR

This paper explores combining distributional thesaurus network embeddings with traditional word vectors, demonstrating significant improvements in NLP tasks without relying on handcrafted lexical resources.

Contribution

It introduces a novel method to embed distributional thesaurus networks into dense vectors and shows that combining these with existing word vectors enhances NLP task performance.

Findings

Combined embeddings outperform individual methods in word similarity tasks

Distributional thesaurus embeddings achieve comparable results to lexical resource-based methods

The approach improves performance in synonym and analogy detection tasks

Abstract

Distributed representations of words learned from text have proved to be successful in various natural language processing tasks in recent times. While some methods represent words as vectors computed from text using predictive model (Word2vec) or dense count based model (GloVe), others attempt to represent these in a distributional thesaurus network structure where the neighborhood of a word is a set of words having adequate context overlap. Being motivated by recent surge of research in network embedding techniques (DeepWalk, LINE, node2vec etc.), we turn a distributional thesaurus network into dense word vectors and investigate the usefulness of distributional thesaurus embedding in improving overall word representation. This is the first attempt where we show that combining the proposed word representation obtained by distributional thesaurus embedding with the state-of-the-art word representations helps in improving the performance by a significant margin when evaluated against NLP tasks like word similarity and relatedness, synonym detection, analogy detection. Additionally, we show that even without using any handcrafted lexical resources we can come up with representations having comparable performance in the word similarity and relatedness tasks compared to the representations where a lexical resource has been used.