Weight Initialization in Neural Language Models

TL;DR

This paper explores a hybrid approach combining vector space models like Word2Vec with ontological methods like WordNet to improve semantic similarity and relatedness measures in NLP applications.

Contribution

It proposes integrating statistical and ontological methods to leverage their combined strengths for better semantic representations.

Findings

Hybrid methods outperform pure vector space models in semantic tasks.

Combining Word2Vec with WordNet enhances semantic similarity accuracy.

The approach bridges the gap between semantic similarity and relatedness measures.

Abstract

Semantic Similarity is an important application which finds its use in many downstream NLP applications. Though the task is mathematically defined, semantic similarity's essence is to capture the notions of similarity impregnated in humans. Machines use some heuristics to calculate the similarity between words, but these are typically corpus dependent or are useful for specific domains. The difference between Semantic Similarity and Semantic Relatedness motivates the development of new algorithms. For a human, the word car and road are probably as related as car and bus. But this may not be the case for computational methods. Ontological methods are good at encoding Semantic Similarity and Vector Space models are better at encoding Semantic Relatedness. There is a dearth of methods which leverage ontologies to create better vector representations. The aim of this proposal is to explore in the direction of a hybrid method which combines statistical/vector space methods like Word2Vec and Ontological methods like WordNet to leverage the advantages provided by both.