Augmenting Document Representations For Dense Retrieval With Interpolation And Perturbation

Abstract

Dense retrieval models, which aim at retrieving the most relevant document for an input query on a dense representation space, have gained considerable attention for their remarkable success. Yet, dense models require a vast amount of labeled training data for notable performance, whereas it is often challenging to acquire query-document pairs annotated by humans. To tackle this problem, we propose a simple but effective Document Augmentation for dense Retrieval (DAR) framework, which augments the representations of documents with their interpolation and perturbation. We validate the performance of DAR on retrieval tasks with two benchmark datasets, showing that the proposed DAR significantly outperforms relevant baselines on the dense retrieval of both the labeled and unlabeled documents.

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyjeong2022augmenting

Related papers

• Llm-augmented Retrieval: Enhancing Retrieval Models Through Language Models And Doc-level Embedding (2024)0.00
• How To Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval (2023)11.39
• Improving Document Representations By Generating Pseudo Query Embeddings For Dense Retrieval (2021)9.41
• Learning Diverse Document Representations With Deep Query Interactions For Dense Retrieval (2022)2.51
• Improving Query Representations For Dense Retrieval With Pseudo Relevance Feedback (2021)12.10
• Disentangled Modeling Of Domain And Relevance For Adaptable Dense Retrieval (2022)0.00
• Soft Prompt Tuning For Augmenting Dense Retrieval With Large Language Models (2023)9.41
• Expandr: Teaching Dense Retrievers Beyond Queries With LLM Guidance (2025)3.25