Analysing The Robustness Of Dual Encoders For Dense Retrieval Against Misspellings

Abstract

Dense retrieval is becoming one of the standard approaches for document and passage ranking. The dual-encoder architecture is widely adopted for scoring question-passage pairs due to its efficiency and high performance. Typically, dense retrieval models are evaluated on clean and curated datasets. However, when deployed in real-life applications, these models encounter noisy user-generated text. That said, the performance of state-of-the-art dense retrievers can substantially deteriorate when exposed to noisy text. In this work, we study the robustness of dense retrievers against typos in the user question. We observe a significant drop in the performance of the dual-encoder model when encountering typos and explore ways to improve its robustness by combining data augmentation with contrastive learning. Our experiments on two large-scale passage ranking and open-domain question answering datasets show that our proposed approach outperforms competing approaches. Additionally, we perform

Stats

• citations18
• S2 citations—
• github stars0
• HF likes0
• heat score9.59
• arxiv keysidiropoulos2022analysing

Related papers

• Improving The Robustness Of Dense Retrievers Against Typos Via Multi-positive Contrastive Learning (2024)5.84
• Typo-robust Representation Learning For Dense Retrieval (2023)7.50
• Typos-aware Bottlenecked Pre-training For Robust Dense Retrieval (2023)5.84
• Noise-robust Dense Retrieval Via Contrastive Alignment Post Training (2023)0.00
• What Are You Token About? Dense Retrieval As Distributions Over The Vocabulary (2022)8.09
• Pre-train A Discriminative Text Encoder For Dense Retrieval Via Contrastive Span Prediction (2022)10.21
• Towards Robust Ranker For Text Retrieval (2022)5.84
• More Robust Dense Retrieval With Contrastive Dual Learning (2021)11.88