A Study On Passage Re-ranking In Embedding Based Unsupervised Semantic Search

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychowdhury2018a

Related papers

• Hybrid And Collaborative Passage Reranking (2023)2.26
• Evaluating The Impact Of Word Embeddings On Similarity Scoring In Practical Information Retrieval (2026)0.00
• Utilizing Embeddings For Ad-hoc Retrieval By Document-to-document Similarity (2017)0.00
• Multiple Visual-semantic Embedding For Video Retrieval From Query Sentence (2020)2.26
• A Passage-based Approach To Learning To Rank Documents (2019)8.60
• Vectorsearch: Enhancing Document Retrieval With Semantic Embeddings And Optimized Search (2024)0.00
• Embedding-based Zero-shot Retrieval Through Query Generation (2020)0.00
• Context Is Gold To Find The Gold Passage: Evaluating And Training Contextual Document Embeddings (2025)5.62