知识蒸馏是将知识从强大的教师转移到有效的学生模型的有效方法。理想情况下，我们希望老师越好，学生越好。但是，这种期望并不总是成真。通常，由于教师和学生之间的不可忽略的差距，更好的教师模型通过蒸馏导致不良学生。为了弥合差距，我们提出了一种渐进式蒸馏方法，以进行致密检索。产品由教师渐进式蒸馏和数据进行渐进的蒸馏组成，以逐步改善学生。我们对五个广泛使用的基准，MARCO通道，TREC Passage 19，TREC文档19，MARCO文档和自然问题进行了广泛的实验，其中POD在蒸馏方法中实现了密集检索的最新方法。代码和模型将发布。

Knowledge distillation is often used to transfer knowledge from a strong teacher model to a relatively weak student model. Traditional knowledge distillation methods include response-based methods and feature-based methods. Response-based methods are used the most widely but suffer from lower upper limit of model performance, while feature-based methods have constraints on the vocabularies and tokenizers. In this paper, we propose a tokenizer-free method liberal feature-based distillation (LEAD). LEAD aligns the distribution between teacher model and student model, which is effective, extendable, portable and has no requirements on vocabularies, tokenizer, or model architecture. Extensive experiments show the effectiveness of LEAD on several widely-used benchmarks, including MS MARCO Passage, TREC Passage 19, TREC Passage 20, MS MARCO Document, TREC Document 19 and TREC Document 20.

To improve the performance of the dual-encoder retriever, one effective approach is knowledge distillation from the cross-encoder ranker. Existing works construct the candidate passages following the supervised learning setting where a query is paired with a positive passage and a batch of negatives. However, through empirical observation, we find that even the hard negatives from advanced methods are still too trivial for the teacher to distinguish, preventing the teacher from transferring abundant dark knowledge to the student through its soft label. To alleviate this issue, we propose ADAM, a knowledge distillation framework that can better transfer the dark knowledge held in the teacher with Adaptive Dark exAMples. Different from previous works that only rely on one positive and hard negatives as candidate passages, we create dark examples that all have moderate relevance to the query through mixing-up and masking in discrete space. Furthermore, as the quality of knowledge held in different training instances varies as measured by the teacher's confidence score, we propose a self-paced distillation strategy that adaptively concentrates on a subset of high-quality instances to conduct our dark-example-based knowledge distillation to help the student learn better. We conduct experiments on two widely-used benchmarks and verify the effectiveness of our method.

当前的密集文本检索模型面临两个典型的挑战。首先，他们采用暹罗双重编码架构来独立编码查询和文档，以快速索引和搜索，同时忽略了较细粒度的术语互动。这导致了次优的召回表现。其次，他们的模型培训高度依赖于负面抽样技术，以在其对比损失中构建负面文档。为了应对这些挑战，我们提出了对抗猎犬速率（AR2），它由双重编码猎犬加上跨编码器等级组成。这两种模型是根据最小群体对手的共同优化的：检索员学会了检索负面文件以欺骗排名者，而排名者学会了对包括地面和检索的候选人进行排名，并提供渐进的直接反馈对双编码器检索器。通过这款对抗性游戏，猎犬逐渐生产出更难的负面文件来训练更好的排名者，而跨编码器排名者提供了渐进式反馈以改善检索器。我们在三个基准测试基准上评估AR2。实验结果表明，AR2始终如一地胜过现有的致密回收者方法，并在所有这些方法上实现了新的最新结果。这包括对自然问题的改进R@5％至77.9％（+2.1％），Triviaqa R@5％至78.2％（+1.4）和MS-Marco MRR@10％至39.5％（+1.3％）。代码和型号可在https://github.com/microsoft/ar2上找到。

Long document retrieval aims to fetch query-relevant documents from a large-scale collection, where knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder. However, in contrast to passages or sentences, retrieval on long documents suffers from the scope hypothesis that a long document may cover multiple topics. This maximizes their structure heterogeneity and poses a granular-mismatch issue, leading to an inferior distillation efficacy. In this work, we propose a new learning framework, fine-grained distillation (FGD), for long-document retrievers. While preserving the conventional dense retrieval paradigm, it first produces global-consistent representations crossing different fine granularity and then applies multi-granular aligned distillation merely during training. In experiments, we evaluate our framework on two long-document retrieval benchmarks, which show state-of-the-art performance.

Dense retrieval aims to map queries and passages into low-dimensional vector space for efficient similarity measuring, showing promising effectiveness in various large-scale retrieval tasks. Since most existing methods commonly adopt pre-trained Transformers (e.g. BERT) for parameter initialization, some work focuses on proposing new pre-training tasks for compressing the useful semantic information from passages into dense vectors, achieving remarkable performances. However, it is still challenging to effectively capture the rich semantic information and relations about passages into the dense vectors via one single particular pre-training task. In this work, we propose a multi-task pre-trained model, MASTER, that unifies and integrates multiple pre-training tasks with different learning objectives under the bottlenecked masked autoencoder architecture. Concretely, MASTER utilizes a multi-decoder architecture to integrate three types of pre-training tasks: corrupted passages recovering, related passage recovering and PLMs outputs recovering. By incorporating a shared deep encoder, we construct a representation bottleneck in our architecture, compressing the abundant semantic information across tasks into dense vectors. The first two types of tasks concentrate on capturing the semantic information of passages and relationships among them within the pre-training corpus. The third one can capture the knowledge beyond the corpus from external PLMs (e.g. GPT-2). Extensive experiments on several large-scale passage retrieval datasets have shown that our approach outperforms the previous state-of-the-art dense retrieval methods. Our code and data are publicly released in https://github.com/microsoft/SimXNS

尽管配备的远景和语言预处理（VLP）在过去两年中取得了显着的进展，但它遭受了重大缺点：VLP型号不断增加的尺寸限制了其部署到现实世界的搜索场景（高潜伏期是不可接受的）。为了减轻此问题，我们提出了一种新颖的插件动态对比度蒸馏（DCD）框架，以压缩ITR任务的大型VLP模型。从技术上讲，我们面临以下两个挑战：1）由于GPU内存有限，在处理交叉模式融合功能期间优化了太多的负样本，因此很难直接应用于跨模式任务，因此很难直接应用于跨模式任务。 。 2）从不同的硬样品中静态优化学生网络的效率效率低下，这些样本对蒸馏学习和学生网络优化具有不同的影响。我们试图从两点克服这些挑战。首先，为了实现多模式对比度学习并平衡培训成本和效果，我们建议使用教师网络估算学生的困难样本，使学生吸收了预培训的老师的强大知识，并掌握知识来自硬样品。其次，要从硬样品对学习动态，我们提出动态蒸馏以动态学习不同困难的样本，从更好地平衡知识和学生的自学能力的困难的角度。我们成功地将我们提出的DCD策略应用于两个最先进的视觉语言预处理模型，即vilt和仪表。关于MS-Coco和FlickR30K基准测试的广泛实验显示了我们DCD框架的有效性和效率。令人鼓舞的是，与现有的ITR型号相比，我们可以至少加快推断至少129美元的$ \ times $。

基于语义空间中密集表示的检索模型已成为第一阶段检索的必不可少的分支。这些检索员受益于代表学习朝着压缩全球序列级嵌入的进步。但是，它们很容易忽略本地的显着短语和实体在文本中提到的，这些短语通常在第一阶段的检索中扮演枢轴角色。为了减轻这种弱点，我们提议使一个密集的检索器对齐一个表现出色的词典意识代表模型。对齐方式是通过弱化的知识蒸馏来实现的，以通过两个方面来启发猎犬 - 1）词汇扬声的对比目标，以挑战密集编码器和2）一个配对的等级正规化，以使密集的模型的行为倾向于其他人的行为。我们在三个公共基准上评估了我们的模型，这表明，凭借可比的词典觉得回收犬作为老师，我们提议的密集人可以带来一致而重大的改进，甚至超过教师。此外，我们发现我们对密集猎犬的改进是与标准排名蒸馏的补充，这可以进一步提高最先进的性能。

排名者在事实上的“检索和rerank”管道中起着必不可少的作用，但其训练仍然落后 - 从中​​度的负面因素或/和/和/和作为回收者的辅助模块中学习。在这项工作中，我们首先确定了强大的排名者的两个主要障碍，即是由训练有素的回猎犬和非理想的负面负面的固有标签噪声，该噪声是为高能力的排名所采样的。因此，我们提出多个检索器，因为负面发电机改善了排名者的鲁棒性，其中i）涉及广泛的分发标签噪声，使排名者与每个噪声分布相对，而ii）与排名相对较接近排名负分配，导致更具挑战性的培训。为了评估我们的强大排名者（称为r $^2 $ anker），我们在各种环境中进行了有关流行通道检索基准测试的各种实验，包括BM25级，全等级，回收者蒸馏等。经验结果验证了新的州 - 新州 - 新州 - 我们模型的效果。

在本文中，我们提出了一个新的密集检索模型，该模型通过深度查询相互作用学习了各种文档表示。我们的模型使用一组生成的伪Queries编码每个文档，以获取查询信息的多视文档表示。它不仅具有较高的推理效率，例如《香草双编码模型》，而且还可以在文档编码中启用深度查询文档的交互，并提供多方面的表示形式，以更好地匹配不同的查询。几个基准的实验证明了所提出的方法的有效性，表现出色的双重编码基准。

Although continually extending an existing NMT model to new domains or languages has attracted intensive interest in recent years, the equally valuable problem of continually improving a given NMT model in its domain by leveraging knowledge from an unlimited number of existing NMT models is not explored yet. To facilitate the study, we propose a formal definition for the problem named knowledge accumulation for NMT (KA-NMT) with corresponding datasets and evaluation metrics and develop a novel method for KA-NMT. We investigate a novel knowledge detection algorithm to identify beneficial knowledge from existing models at token level, and propose to learn from beneficial knowledge and learn against other knowledge simultaneously to improve learning efficiency. To alleviate catastrophic forgetting, we further propose to transfer knowledge from previous to current version of the given model. Extensive experiments show that our proposed method significantly and consistently outperforms representative baselines under homogeneous, heterogeneous, and malicious model settings for different language pairs.

The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and document. To alleviate this, recent work expects to get query-informed representations of documents. During training, it expands the document with a real query, while replacing the real query with a generated pseudo query at inference. This discrepancy between training and inference makes the dense retrieval model pay more attention to the query information but ignore the document when computing the document representation. As a result, it even performs worse than the vanilla dense retrieval model, since its performance depends heavily on the relevance between the generated queries and the real query. In this paper, we propose a curriculum sampling strategy, which also resorts to the pseudo query at training and gradually increases the relevance of the generated query to the real query. In this way, the retrieval model can learn to extend its attention from the document only to both the document and query, hence getting high-quality query-informed document representations. Experimental results on several passage retrieval datasets show that our approach outperforms the previous dense retrieval methods1.

Large transformer models can highly improve Answer Sentence Selection (AS2) tasks, but their high computational costs prevent their use in many real-world applications. In this paper, we explore the following research question: How can we make the AS2 models more accurate without significantly increasing their model complexity? To address the question, we propose a Multiple Heads Student architecture (named CERBERUS), an efficient neural network designed to distill an ensemble of large transformers into a single smaller model. CERBERUS consists of two components: a stack of transformer layers that is used to encode inputs, and a set of ranking heads; unlike traditional distillation technique, each of them is trained by distilling a different large transformer architecture in a way that preserves the diversity of the ensemble members. The resulting model captures the knowledge of heterogeneous transformer models by using just a few extra parameters. We show the effectiveness of CERBERUS on three English datasets for AS2; our proposed approach outperforms all single-model distillations we consider, rivaling the state-of-the-art large AS2 models that have 2.7x more parameters and run 2.5x slower. Code for our model is available at https://github.com/amazon-research/wqa-cerberus

缺乏标记数据是关系提取的主要障碍。通过将未标记的样本作为额外培训数据注释，已经证明，半监督联系提取（SSRE）已被证明是一个有希望的方法。沿着这条线几乎所有先前的研究采用多种模型来使注释通过从这些模型中获取交叉路口集的预测结果来更加可靠。然而，差异集包含有关未标记数据的丰富信息，并通过事先研究忽略了忽视。在本文中，我们建议不仅从共识中学习，而且还要学习SSRE中不同模型之间的分歧。为此，我们开发了一种简单且一般的多教师蒸馏（MTD）框架，可以轻松集成到任何现有的SSRE方法中。具体来说，我们首先让教师对应多个模型，并在SSRE方法中选择最后一次迭代的交叉点集中的样本，以便像往常一样增加标记的数据。然后，我们将类分布转移为差异设置为软标签以指导学生。我们最后使用训练有素的学生模型进行预测。两个公共数据集上的实验结果表明，我们的框架显着促进了基础SSRE方法的性能，具有相当低的计算成本。

密集的段落检索旨在根据查询和段落的密集表示（即矢量）从大型语料库中检索查询的相关段落。最近的研究探索了改善预训练的语言模型，以提高密集的检索性能。本文提出了COT-MAE（上下文掩盖自动编码器），这是一种简单而有效的生成性预训练方法，可用于密集通道检索。 COT-MAE采用了不对称的编码器架构，该体系结构学会通过自我监督和上下文监督的掩盖自动编码来将句子语义压缩到密集的矢量中。精确，自我监督的掩盖自动编码学会学会为文本跨度内的令牌的语义建模，并学习上下文监督的蒙版自动编码学学习以建模文本跨度之间的语义相关性。我们对大规模通道检索基准进行实验，并显示出对强基础的大量改进，证明了COT-MAE的效率很高。

知识蒸馏（KD）已广泛发展并增强了各种任务。经典的KD方法将KD损失添加到原始的跨熵（CE）损失中。我们尝试分解KD损失，以探索其与CE损失的关系。令人惊讶的是，我们发现它可以被视为CE损失和额外损失的组合，其形式与CE损失相同。但是，我们注意到额外的损失迫使学生学习教师绝对概率的相对可能性。此外，这两个概率的总和是不同的，因此很难优化。为了解决这个问题，我们修改了配方并提出分布式损失。此外，我们将教师的目标输出作为软目标，提出软损失。结合软损失和分布式损失，我们提出了新的KD损失（NKD）。此外，我们将学生的目标输出稳定，将其视为无需教师的培训的软目标，并提出了无教师的新KD损失（TF-NKD）。我们的方法在CIFAR-100和Imagenet上实现了最先进的性能。例如，以Resnet-34为老师，我们将Imagenet TOP-1的RESNET18的TOP-1精度从69.90％提高到71.96％。在没有教师的培训中，Mobilenet，Resnet-18和Swintransformer-tiny的培训占70.04％，70.76％和81.48％，分别比基线高0.83％，0.86％和0.30％。该代码可在https://github.com/yzd-v/cls_kd上找到。

最初引入了知识蒸馏，以利用来自单一教师模型的额外监督为学生模型培训。为了提高学生表现，最近的一些变体试图利用多个教师利用不同的知识来源。然而，现有研究主要通过对多种教师预测的平均或将它们与其他无标签策略相结合，将知识集成在多种来源中，可能在可能存在低质量的教师预测存在中误导学生。为了解决这个问题，我们提出了信心感知的多教师知识蒸馏（CA-MKD），该知识蒸馏（CA-MKD）在地面真理标签的帮助下，适用于每个教师预测的样本明智的可靠性，与那些接近单热的教师预测标签分配了大量的重量。此外，CA-MKD包含中间层，以进一步提高学生表现。广泛的实验表明，我们的CA-MKD始终如一地优于各种教师学生架构的所有最先进的方法。

This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a wide range of tasks. The model is trained in a contrastive manner with weak supervision signals from our curated large-scale text pair dataset (called CCPairs). E5 can be readily used as a general-purpose embedding model for any tasks requiring a single-vector representation of texts such as retrieval, clustering, and classification, achieving strong performance in both zero-shot and fine-tuned settings. We conduct extensive evaluations on 56 datasets from the BEIR and MTEB benchmarks. For zero-shot settings, E5 is the first model that outperforms the strong BM25 baseline on the BEIR retrieval benchmark without using any labeled data. When fine-tuned, E5 obtains the best results on the MTEB benchmark, beating existing embedding models with 40x more parameters.

无数据知识蒸馏（DFKD）的目的是在没有培训数据的情况下培训从教师网络的轻量级学生网络。现有方法主要遵循生成信息样本的范式，并通过针对数据先验，边界样本或内存样本来逐步更新学生模型。但是，以前的DFKD方法很难在不同的训练阶段动态调整生成策略，这反过来又很难实现高效且稳定的训练。在本文中，我们探讨了如何从课程学习（CL）的角度来教学学生，并提出一种新方法，即“ CUDFKD”，即“使用课程的无数据知识蒸馏”。它逐渐从简单的样本到困难的样本学习，这类似于人类学习的方式。此外，我们还提供了对主要化最小化（MM）算法的理论分析，并解释了CUDFKD的收敛性。在基准数据集上进行的实验表明，使用简单的课程设计策略，CUDFKD可以在最先进的DFKD方法和不同的基准测试中实现最佳性能，例如CIFAR10上RESNET18模型的95.28 \％TOP1的精度，这是更好的而不是从头开始培训数据。训练很快，在30个时期内达到90 \％的最高精度，并且训练期间的差异稳定。同样在本文中，还分析和讨论了CUDFKD的适用性。

Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In general, the temperature controls the discrepancy between two distributions and can faithfully determine the difficulty level of the distillation task. Keeping a constant temperature, i.e., a fixed level of task difficulty, is usually sub-optimal for a growing student during its progressive learning stages. In this paper, we propose a simple curriculum-based technique, termed Curriculum Temperature for Knowledge Distillation (CTKD), which controls the task difficulty level during the student's learning career through a dynamic and learnable temperature. Specifically, following an easy-to-hard curriculum, we gradually increase the distillation loss w.r.t. the temperature, leading to increased distillation difficulty in an adversarial manner. As an easy-to-use plug-in technique, CTKD can be seamlessly integrated into existing knowledge distillation frameworks and brings general improvements at a negligible additional computation cost. Extensive experiments on CIFAR-100, ImageNet-2012, and MS-COCO demonstrate the effectiveness of our method. Our code is available at https://github.com/zhengli97/CTKD.