Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document. This inevitably brings the challenge of efficient open-space evidence retrieval to support the inference of cross-document relations, along with the challenge of multi-hop reasoning on top of entities and evidence scattered in an open set of documents. To combat these challenges, we propose Mr.CoD, a multi-hop evidence retrieval method based on evidence path mining and ranking with adapted dense retrievers. We explore multiple variants of retrievers to show evidence retrieval is an essential part in cross-document RE. Experiments on CodRED show that evidence retrieval with Mr.Cod effectively acquires cross-document evidence that essentially supports open-setting cross-document RE. Additionally, we show that Mr.CoD facilitates evidence retrieval and boosts end-to-end RE performance with effective multi-hop reasoning in both closed and open settings of RE.
translated by 谷歌翻译
Two key obstacles in biomedical relation extraction (RE) are the scarcity of annotations and the prevalence of instances without explicitly pre-defined labels due to low annotation coverage. Existing approaches, which treat biomedical RE as a multi-class classification task, often result in poor generalization in low-resource settings and do not have the ability to make selective prediction on unknown cases but give a guess from seen relations, hindering the applicability of those approaches. We present NBR, which converts biomedical RE as natural language inference formulation through indirect supervision. By converting relations to natural language hypotheses, NBR is capable of exploiting semantic cues to alleviate annotation scarcity. By incorporating a ranking-based loss that implicitly calibrates abstinent instances, NBR learns a clearer decision boundary and is instructed to abstain on uncertain instances. Extensive experiments on three widely-used biomedical RE benchmarks, namely ChemProt, DDI and GAD, verify the effectiveness of NBR in both full-set and low-resource regimes. Our analysis demonstrates that indirect supervision benefits biomedical RE even when a domain gap exists, and combining NLI knowledge with biomedical knowledge leads to the best performance gains.
translated by 谷歌翻译
最近,对时间变化的知识图或时间知识图(TKG)的学术兴趣越来越高。先前的研究表明,使用历史信息的TKG推理的多种方法。但是,在不同时间戳上此类信息中对层次结构的关注较少。鉴于TKG是基于时间的一系列知识图,因此序列中的年代学衍生了图之间的层次结构。此外,每个知识图都有其层次结构级别,可能相互不同。为了解决TKG中的这些层次结构特征,我们提出了HyperVC,它利用比欧几里得空间更好地编码层次结构的双曲线空间。不同时间戳上知识图之间的时间顺序结构是通过将知识图作为矢量嵌入通用双曲线空间中的矢量来表示的。此外,通过调整其实体和关系的双曲线嵌入的曲率来表示,知识图的各种层次级别。四个基准数据集的实验显示出很大的改进,尤其是在层次级别较高的数据集上。
translated by 谷歌翻译
临床领域中的事件提取是一个探索较少的研究领域。除了大量的特定领域的行话外,缺乏培训数据,包括较长的实体,具有模糊的边界,使该任务尤其具有挑战性。在本文中,我们介绍了DICE,这是一种用于临床事件提取的强大而数据效率的生成模型。骰子框架事件提取作为有条件的生成问题,并利用域专家提供的描述来提高低资源设置下的性能。此外,DICE学会了与辅助提及的识别任务一起定位和约束生物医学提及,该任务与事件提取任务共同培训,以利用任务间的依赖性,并进一步纳入确定的提及作为其各自任务的触发和论证候选者。我们还介绍了MacCrobat-EE,这是第一个带有事件参数注释的临床事件提取数据集。我们的实验证明了在临床领域的低数据设置下骰子的鲁棒性,以及将柔性关节训练并提及标记纳入生成方法的好处。
translated by 谷歌翻译
对象检测是各种关键计算机视觉任务的基础,例如分割,对象跟踪和事件检测。要以令人满意的精度训练对象探测器,需要大量数据。但是,由于注释大型数据集涉及大量劳动力,这种数据策展任务通常被外包给第三方或依靠志愿者。这项工作揭示了此类数据策展管道的严重脆弱性。我们提出MACAB,即使数据策展人可以手动审核图像,也可以将干净的图像制作清洁的图像将后门浸入对象探测器中。我们观察到,当后门被不明确的天然物理触发器激活时,在野外实现了错误分类和披肩的后门效应。与带有清洁标签的现有图像分类任务相比,带有清洁通道的非分类对象检测具有挑战性,这是由于每个帧内有多个对象的复杂性,包括受害者和非视野性对象。通过建设性地滥用深度学习框架使用的图像尺度函数,II结合了所提出的对抗性清洁图像复制技术,以及在考虑到毒品数据选择标准的情况下,通过建设性地滥用图像尺度尺度,可以确保MACAB的功效。广泛的实验表明,在各种现实世界中,MacAB在90%的攻击成功率中表现出超过90%的攻击成功率。这包括披肩和错误分类后门效应,甚至限制了较小的攻击预算。最先进的检测技术无法有效地识别中毒样品。全面的视频演示位于https://youtu.be/ma7l_lpxkp4上,该演示基于yolov4倒置的毒药率为0.14%,yolov4 clokaking后门和更快的速度R-CNN错误分类后门。
translated by 谷歌翻译
后门深度学习(DL)模型的行为通常在清洁输入上,但在触发器输入时不端行为,因为后门攻击者希望为DL模型部署构成严重后果。最先进的防御是限于特定的后门攻击(源无关攻击)或在该机器学习(ML)专业知识或昂贵的计算资源中不适用于源友好的攻击。这项工作观察到所有现有的后门攻击都具有不可避免的内在弱点,不可转换性,即触发器输入劫持劫持模型,但不能对另一个尚未植入同一后门的模型有效。通过此密钥观察,我们提出了不可转换性的反向检测(NTD)来识别运行时在运行时的模型欠测试(MUT)的触发输入。特定,NTD允许潜在的回溯静电预测输入的类别。同时,NTD利用特征提取器(FE)来提取输入的特征向量,并且从其预测类随机拾取的一组样本,然后比较FE潜在空间中的输入和样本之间的相似性。如果相似性低,则输入是对逆势触发输入;否则,良性。 FE是一个免费的预训练模型,私下从开放平台保留。随着FE和MUT来自不同来源,攻击者非常不可能将相同的后门插入其中两者。由于不可转换性,不能将突变处工作的触发效果转移到FE,使NTD对不同类型的后门攻击有效。我们在三个流行的定制任务中评估NTD,如面部识别,交通标志识别和一般动物分类,结果确认NDT具有高效率(低假验收率)和具有低检测延迟的可用性(低误报率)。
translated by 谷歌翻译
尽管深度神经网络模型在各种应用程序中表现出出色的性能,但它们的较大模型大小和广泛的浮点操作使移动计算平台上的部署成为主要挑战,尤其是在物联网设备上。一种吸引人的解决方案是模型量化,可降低模型大小并使用微控制器通常支持的整数操作。为此,1位量化的DNN模型或深二进制神经网络可最大化存储效率,其中BNN模型中的每个参数仅具有1位。在本文中,我们提出了一个可重构的BNN(RBNN),以进一步扩大资源约束的物联网设备的内存效率。通常,可以根据需要重新配置RBNN,以实现具有相同参数集的M(m> 1)不同的任务,因此只有一个任务决定了内存要求。换句话说,通过时间M改善了内存利用率。我们的广泛实验证实了多达七个常用的任务可以共存(M的值更大)。这些具有不同类别的任务在三个二氧化流行的DNN体系结构(包括VGG,Resnet和ReactNet)上没有准确性或微不足道的准确性下降。这些任务跨越了不同域,例如本文验证的计算机视觉和音频域,并以模型体系结构可以服务于这些跨域任务的先决条件。为了保护RBNN模型的知识属性,可以通过用户密钥和由固有硬件指纹生成的设备唯一的根键来控制重新配置。通过这样做,RBNN模型只能使用每个授权设备的每个付费用户使用,从而使用户和模型提供商受益。
translated by 谷歌翻译
多文件摘要(MDS)是信息聚合的有效工具,它从与主题相关文档集群生成信息和简洁的摘要。我们的调查是,首先,系统地概述了最近的基于深度学习的MDS模型。我们提出了一种新的分类学,总结神经网络的设计策略,并进行全面的最先进的概要。我们突出了在现有文献中很少讨论的各种客观函数之间的差异。最后,我们提出了与这个新的和令人兴奋的领域有关的几个方向。
translated by 谷歌翻译
Feature selection helps reduce data acquisition costs in ML, but the standard approach is to train models with static feature subsets. Here, we consider the dynamic feature selection (DFS) problem where a model sequentially queries features based on the presently available information. DFS is often addressed with reinforcement learning (RL), but we explore a simpler approach of greedily selecting features based on their conditional mutual information. This method is theoretically appealing but requires oracle access to the data distribution, so we develop a learning approach based on amortized optimization. The proposed method is shown to recover the greedy policy when trained to optimality and outperforms numerous existing feature selection methods in our experiments, thus validating it as a simple but powerful approach for this problem.
translated by 谷歌翻译
Artificial intelligence (AI) in the form of deep learning bears promise for drug discovery and chemical biology, $\textit{e.g.}$, to predict protein structure and molecular bioactivity, plan organic synthesis, and design molecules $\textit{de novo}$. While most of the deep learning efforts in drug discovery have focused on ligand-based approaches, structure-based drug discovery has the potential to tackle unsolved challenges, such as affinity prediction for unexplored protein targets, binding-mechanism elucidation, and the rationalization of related chemical kinetic properties. Advances in deep learning methodologies and the availability of accurate predictions for protein tertiary structure advocate for a $\textit{renaissance}$ in structure-based approaches for drug discovery guided by AI. This review summarizes the most prominent algorithmic concepts in structure-based deep learning for drug discovery, and forecasts opportunities, applications, and challenges ahead.
translated by 谷歌翻译