Unsupervised Dense Information Retrieval with Contrastive Learning

Abstract

Recently, information retrieval has seen the emergence of dense retrievers, using neural networks, as an alternative to classical sparse methods based on term-frequency. These models have obtained state-of-the-art results on datasets and tasks where large training sets are available. However, they do not transfer well to new applications with no training data, and are outperformed by unsupervised term-frequency methods such as BM25. In this work, we explore the limits of contrastive learning as a way to train unsupervised dense retrievers and show that it leads to strong performance in various retrieval settings. On the BEIR benchmark our unsupervised model outperforms BM25 on 11 out of 15 datasets for the Recall@100. When used as pre-training before fine-tuning, either on a few thousands in-domain examples or on the large MS~MARCO dataset, our contrastive model leads to improvements on the BEIR benchmark. Finally, we evaluate our approach for multi-lingual retrieval, where training data is even scarcer than for English, and show that our approach leads to strong unsupervised performance. Our model also exhibits strong cross-lingual transfer when fine-tuned on supervised English data only and evaluated on low resources language such as Swahili. We show that our unsupervised models can perform cross-lingual retrieval between different scripts, such as retrieving English documents from Arabic queries, which would not be possible with term matching methods.

Cited by in corpus (16)

• Generative Relevance Feedback with Large Language Models
• Learning Retrieval Augmentation for Personalized Dialogue Generation
• Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage Training
• SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes
• Decoy Effect In Search Interaction: Understanding User Behavior and Measuring System Vulnerability
• Efficient Tuning of Large Language Models for Knowledge-Grounded Dialogue Generation
• Variational Open-Domain Question Answering
• Early Exit Strategies for Approximate k-NN Search in Dense Retrieval
• Exploring ${\ell }_0$ Sparsification for Inference-free Sparse Retrievers
• Reply with Sticker: New Dataset and Model for Sticker Retrieval
• Multi-Modality Transformer for E-Commerce: Inferring User Purchase Intention to Bridge the Query-Product Gap
• DESIRE-ME: Domain-Enhanced Supervised Information REtrieval using Mixture-of-Experts
• Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework
• Unsupervised Dense Retrieval Training with Web Anchors
• Simple Domain Adaptation for Sparse Retrievers
• UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer Learning