A Study on Passage Re-ranking in Embedding based Unsupervised Semantic Search

TL;DR

This paper introduces a novel passage re-ranking method called VCVB that combines compositional and contextual similarity for improved unsupervised semantic search, validated through empirical benchmarks.

Contribution

It proposes a new compositional similarity approach, VCVB, addressing limitations of existing methods and explores universal sentence embeddings for better passage ranking.

Findings

VCVB improves passage ranking accuracy.

Universal sentence embeddings enhance semantic search.

Empirical results show state-of-the-art performance.

Abstract

State of the art approaches for (embedding based) unsupervised semantic search exploits either compositional similarity (of a query and a passage) or pair-wise word (or term) similarity (from the query and the passage). By design, word based approaches do not incorporate similarity in the larger context (query/passage), while compositional similarity based approaches are usually unable to take advantage of the most important cues in the context. In this paper we propose a new compositional similarity based approach, called variable centroid vector (VCVB), that tries to address both of these limitations. We also presents results using a different type of compositional similarity based approach by exploiting universal sentence embedding. We provide empirical evaluation on two different benchmarks.