Evaluating the impact of word embeddings on similarity scoring in practical information retrieval

TL;DR

This paper demonstrates that combining Word Movers Distance with pre-trained word embeddings significantly improves semantic similarity measurement in information retrieval, outperforming existing models across various datasets.

Contribution

It introduces a novel similarity evaluation approach using WMD with word embeddings, showing superior performance over traditional centroid-based methods.

Findings

WMD + GloVe outperforms Doc2Vec and LSA models.

Significant accuracy improvements in query-response ranking.

Pre-trained embeddings provide domain-agnostic, portable solutions.

Abstract

Search behaviour is characterised using synonymy and polysemy as users often want to search information based on meaning. Semantic representation strategies represent a move towards richer associative connections that can adequately capture this complex usage of language. Vector Space Modelling (VSM) and neural word embeddings play a crucial role in modern machine learning and Natural Language Processing (NLP) pipelines. Embeddings use distributional semantics to represent words, sentences, paragraphs or entire documents as vectors in high dimensional spaces. This can be leveraged by Information Retrieval (IR) systems to exploit the semantic relatedness between queries and answers. This paper evaluates an alternative approach to measuring query statement similarity that moves away from the common similarity measure of centroids of neural word embeddings. Motivated by the Word Movers Distance (WMD) model, similarity is evaluated using the distance between individual words of queries and statements. Results from ranked query and response statements demonstrate significant gains in accuracy using the combined approach of similarity ranking through WMD with the word embedding techniques. The top performing WMD + GloVe combination outperforms all other state-of-the-art retrieval models including Doc2Vec and the baseline LSA model. Along with the significant gains in performance of similarity ranking through WMD, we conclude that the use of pre-trained word embeddings, trained on vast amounts of data, result in domain agnostic language processing solutions that are portable to diverse business use-cases.