Approximate Nearest Neighbor Negative Contrastive Learning For Dense Text Retrieval

Abstract

Conducting text retrieval in a dense learned representation space has many intriguing advantages over sparse retrieval. Yet the effectiveness of dense retrieval (DR) often requires combination with sparse retrieval. In this paper, we identify that the main bottleneck is in the training mechanisms, where the negative instances used in training are not representative of the irrelevant documents in testing. This paper presents Approximate nearest neighbor Negative Contrastive Estimation (ANCE), a training mechanism that constructs negatives from an Approximate Nearest Neighbor (ANN) index of the corpus, which is parallelly updated with the learning process to select more realistic negative training instances. This fundamentally resolves the discrepancy between the data distribution used in the training and testing of DR. In our experiments, ANCE boosts the BERT-Siamese DR model to outperform all competitive dense and sparse retrieval baselines. It nearly matches the accuracy of sparse-ret

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxiong2020approximate

Related papers

• More Robust Dense Retrieval With Contrastive Dual Learning (2021)11.88
• Learning To Retrieve: How To Train A Dense Retrieval Model Effectively And Efficiently (2020)0.00
• Optimizing Dense Retrieval Model Training With Hard Negatives (2021)16.34
• Unsupervised Dense Information Retrieval With Contrastive Learning (2021)0.00
• Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors (2023)4.52
• Unsupervised Dense Retrieval With Conterfactual Contrastive Learning (2024)0.00
• Black-box Adversarial Attacks Against Dense Retrieval Models: A Multi-view Contrastive Learning Method (2023)9.92
• On Approximate Nearest Neighbour Selection For Multi-stage Dense Retrieval (2021)8.35