Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence Regularization

• URL: http://arxiv.org/abs/2401.00165v2
• Date: Sat, 13 Jan 2024 05:56:17 GMT
• Title: Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence Regularization
• Authors: Shiqi Wang, Yeqin Zhang and Cam-Tu Nguyen
• Abstract summary: We propose a novel contrastive confidence regularizer for Noise Contrastive Estimation (NCE) loss. Our analysis shows that the regularizer helps dense retrieval models be more robust against false negatives with a theoretical guarantee.
• Score: 15.204113965411777
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In open-domain Question Answering (QA), dense retrieval is crucial for finding relevant passages for answer generation. Typically, contrastive learning is used to train a retrieval model that maps passages and queries to the same semantic space. The objective is to make similar ones closer and dissimilar ones further apart. However, training such a system is challenging due to the false negative issue, where relevant passages may be missed during data annotation. Hard negative sampling, which is commonly used to improve contrastive learning, can introduce more noise in training. This is because hard negatives are those closer to a given query, and thus more likely to be false negatives. To address this issue, we propose a novel contrastive confidence regularizer for Noise Contrastive Estimation (NCE) loss, a commonly used loss for dense retrieval. Our analysis shows that the regularizer helps dense retrieval models be more robust against false negatives with a theoretical guarantee. Additionally, we propose a model-agnostic method to filter out noisy negative passages in the dataset, improving any downstream dense retrieval models. Through experiments on three datasets, we demonstrate that our method achieves better retrieval performance in comparison to existing state-of-the-art dense retrieval systems.

Related papers

• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Noisy Pair Corrector for Dense Retrieval [59.312376423104055]
  We propose a novel approach called Noisy Pair Corrector (NPC) NPC consists of a detection module and a correction module. We conduct experiments on text-retrieval benchmarks Natural Question and TriviaQA, code-search benchmarks StaQC and SO-DS.
  arXiv  Detail & Related papers  (2023-11-07T08:27:14Z)
• Detrimental Contexts in Open-Domain Question Answering [9.059854023578508]
  We analyze how passages can have a detrimental effect on retrieve-then-read architectures used in question answering. Our findings demonstrate that model accuracy can be improved by 10% on two popular QA datasets by filtering out detrimental passages.
  arXiv  Detail & Related papers  (2023-10-27T11:45:16Z)
• Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training [81.3781338418574]
  We propose relevance-aware contrastive learning. We consistently improve the SOTA unsupervised Contriever model on the BEIR and open-domain QA retrieval benchmarks. Our method can not only beat BM25 after further pre-training on the target corpus but also serves as a good few-shot learner.
  arXiv  Detail & Related papers  (2023-06-05T18:20:27Z)
• Robust Contrastive Learning against Noisy Views [79.71880076439297]
  We propose a new contrastive loss function that is robust against noisy views. We show that our approach provides consistent improvements over the state-of-the-art image, video, and graph contrastive learning benchmarks.
  arXiv  Detail & Related papers  (2022-01-12T05:24:29Z)
• Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval [19.161248757493386]
  We propose our TAiloring neGative Sentences with Discrimination and Correction (TAGS-DC) to generate synthetic sentences automatically as negative samples. To keep the difficulty during training, we mutually improve the retrieval and generation through parameter sharing. In experiments, we verify the effectiveness of our model on MS-COCO and Flickr30K compared with current state-of-the-art models.
  arXiv  Detail & Related papers  (2021-11-05T09:36:41Z)
• Incremental False Negative Detection for Contrastive Learning [95.68120675114878]
  We introduce a novel incremental false negative detection for self-supervised contrastive learning. During contrastive learning, we discuss two strategies to explicitly remove the detected false negatives. Our proposed method outperforms other self-supervised contrastive learning frameworks on multiple benchmarks within a limited compute.
  arXiv  Detail & Related papers  (2021-06-07T15:29:14Z)
• Continual Learning for Fake Audio Detection [62.54860236190694]
  This paper proposes detecting fake without forgetting, a continual-learning-based method, to make the model learn new spoofing attacks incrementally. Experiments are conducted on the ASVspoof 2019 dataset.
  arXiv  Detail & Related papers  (2021-04-15T07:57:05Z)
• Understanding Hard Negatives in Noise Contrastive Estimation [21.602701327267905]
  We develop analytical tools to understand the role of hard negatives. We derive a general form of the score function that unifies various architectures used in text retrieval.
  arXiv  Detail & Related papers  (2021-04-13T14:42:41Z)
• Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval [20.62375162628628]
  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. 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-retrieval-and-BERT-reranking using dot-product in the ANCE-learned representation space and provides almost 100x speed-up.
  arXiv  Detail & Related papers  (2020-07-01T23:15:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.