课堂表达学习是可解释的监督机器学习的分支,越来越重要。在描述逻辑中的类表达式学习的大多数现有方法是搜索算法或基于硬规则的。特别地,基于细化运营商的方法遭受可扩展性问题,因为它们依赖于启发式功能来探索每个学习问题的大搜索空间。我们提出了一系列新的方法,我们配合了合成方法。此系列的实例是从提供的示例中直接计算类表达式。因此,它们不受基于搜索方法的运行时限制,也不存在于基于硬规则的方法的缺乏灵活性。我们研究了这种新型方法的三个实例,该方法使用轻量级神经网络架构从积极的例子组合中综合类表达式。他们对四个基准数据集的评估结果表明,它们可以在平均水平上有效地合成相对于输入示例的高质量类表达。此外,与最先进的方法的比较Celoe和Eltl表明我们在大型本体中实现了更好的F措施。为了重现性目的,我们提供了我们的实施以及在HTTPS://github.com/conceptLengtlearner/nces的公共Github存储库中的预先训练模型
translated by 谷歌翻译
基于细化运算符的概念学习方法探索部分有序的解决方案空间来计算概念,这些空间用作个体的二进制分类模型。然而,这些方法探索的概念的数量可以很容易地增长到数百万的复杂学习问题。这通常会导致不切实际的运行时间。我们建议通过预测解决方案空间探索前的目标概念的长度来缓解这个问题。通过这些手段,我们可以在概念学习期间修剪搜索空间。为了实现这一目标,我们比较四个神经结构,并在四个基准上进行评估。我们的评估结果表明,经常性的神经网络架构在概念长度预测中表现最佳,宏F-MEARY从38%到92%。然后,我们扩展了eloe算法 - 学习ALC概念 - 我们的概念长度预测器。我们的扩展会产生算法剪辑。在我们的实验中,夹子比ALC的其他最先进的概念学习算法速度至少为7.5倍 - 包括Celoe - 并且在4个数据集中学习的3个概念的F-Peasure中实现了重大改进。为了重现性,我们在HTTPS://github.com/conceptlencthLearner/learnlencths中提供我们在公共Github存储库中的实现
translated by 谷歌翻译
知识图中的节点是一个重要任务,例如,预测缺失类型的实体,预测哪些分子导致癌症,或预测哪种药物是有前途的治疗候选者。虽然黑匣子型号经常实现高预测性能,但它们只是hoc后和本地可解释的,并且不允许学习模型轻松丰富域知识。为此,已经提出了学习描述了来自正和否定示例的逻辑概念。然而,学习这种概念通常需要很长时间,最先进的方法为文字数据值提供有限的支持,尽管它们对于许多应用是至关重要的。在本文中,我们提出了Evolearner - 学习ALCQ(D)的进化方法,它是与合格基数限制(Q)和数据属性配对的补充(ALC)的定语语言和数据属性(D)。我们为初始群体贡献了一种新颖的初始化方法:从正示例开始(知识图中的节点),我们执行偏见随机散步并将它们转换为描述逻辑概念。此外,我们通过在决定分割数据的位置时,通过最大化信息增益来提高数据属性的支持。我们表明,我们的方法在结构化机器学习的基准框架SML - 台阶上显着优于现有技术。我们的消融研究证实,这是由于我们的新颖初始化方法和对数据属性的支持。
translated by 谷歌翻译
Semantic Web Rule Language (SWRL) combines OWL (Web Ontology Language) ontologies with Horn Logic rules of the Rule Markup Language (RuleML) family. Being supported by ontology editors, rule engines and ontology reasoners, it has become a very popular choice for developing rule-based applications on top of ontologies. However, SWRL is probably not go-ing to become a WWW Consortium standard, prohibiting industrial acceptance. On the other hand, SPIN (SPARQL Inferencing Notation) has become a de-facto industry standard to rep-resent SPARQL rules and constraints on Semantic Web models, building on the widespread acceptance of SPARQL (SPARQL Protocol and RDF Query Language). In this paper, we ar-gue that the life of existing SWRL rule-based ontology applications can be prolonged by con-verting them to SPIN. To this end, we have developed the SWRL2SPIN tool in Prolog that transforms SWRL rules into SPIN rules, considering the object-orientation of SPIN, i.e. linking rules to the appropriate ontology classes and optimizing them, as derived by analysing the rule conditions.
translated by 谷歌翻译
Knowledge graphs (KG) have served as the key component of various natural language processing applications. Commonsense knowledge graphs (CKG) are a special type of KG, where entities and relations are composed of free-form text. However, previous works in KG completion and CKG completion suffer from long-tail relations and newly-added relations which do not have many know triples for training. In light of this, few-shot KG completion (FKGC), which requires the strengths of graph representation learning and few-shot learning, has been proposed to challenge the problem of limited annotated data. In this paper, we comprehensively survey previous attempts on such tasks in the form of a series of methods and applications. Specifically, we first introduce FKGC challenges, commonly used KGs, and CKGs. Then we systematically categorize and summarize existing works in terms of the type of KGs and the methods. Finally, we present applications of FKGC models on prediction tasks in different areas and share our thoughts on future research directions of FKGC.
translated by 谷歌翻译
在本文中,我们试图通过引入深度学习模型的句法归纳偏见来建立两所学校之间的联系。我们提出了两个归纳偏见的家族,一个家庭用于选区结构,另一个用于依赖性结构。选区归纳偏见鼓励深度学习模型使用不同的单位(或神经元)分别处理长期和短期信息。这种分离为深度学习模型提供了一种方法,可以从顺序输入中构建潜在的层次表示形式,即更高级别的表示由高级表示形式组成,并且可以分解为一系列低级表示。例如,在不了解地面实际结构的情况下,我们提出的模型学会通过根据其句法结构组成变量和运算符的表示来处理逻辑表达。另一方面,依赖归纳偏置鼓励模型在输入序列中找到实体之间的潜在关系。对于自然语言,潜在关系通常被建模为一个定向依赖图,其中一个单词恰好具有一个父节点和零或几个孩子的节点。将此约束应用于类似变压器的模型之后,我们发现该模型能够诱导接近人类专家注释的有向图,并且在不同任务上也优于标准变压器模型。我们认为,这些实验结果为深度学习模型的未来发展展示了一个有趣的选择。
translated by 谷歌翻译
访问公共知识库中可用的大量信息可能对那些不熟悉的SPARQL查询语言的用户可能很复杂。SPARQL中自然语言提出的问题的自动翻译有可能克服这个问题。基于神经机翻译的现有系统非常有效,但在识别出识别出训练集的词汇(OOV)的单词中很容易失败。查询大型本体的时,这是一个严重的问题。在本文中,我们将命名实体链接,命名实体识别和神经计算机翻译相结合,以将自然语言问题的自动转换为SPARQL查询。我们凭经验证明,我们的方法比在纪念碑,QALD-9和LC-QUAD V1上运行实验,我们的方法比现有方法更有效,并且对OOV单词进行了更有效的,并且是现有的方法,这些方法是众所周知的DBPedia的相关数据集。
translated by 谷歌翻译
我用Hunglish2语料库训练神经电脑翻译任务的模型。这项工作的主要贡献在培训NMT模型期间评估不同的数据增强方法。我提出了5种不同的增强方法,这些方法是结构感知的,这意味着而不是随机选择用于消隐或替换的单词,句子的依赖树用作增强的基础。我首先关于神经网络的详细文献综述,顺序建模,神经机翻译,依赖解析和数据增强。经过详细的探索性数据分析和Hunglish2语料库的预处理之后,我使用所提出的数据增强技术进行实验。匈牙利语的最佳型号达到了33.9的BLEU得分,而英国匈牙利最好的模型达到了28.6的BLEU得分。
translated by 谷歌翻译
近年来,人们对少量知识图(FKGC)的兴趣日益增加,该图表旨在推断出关于该关系的一些参考三元组,从而推断出不见了的查询三倍。现有FKGC方法的主要重点在于学习关系表示,可以反映查询和参考三元组共享的共同信息。为此,这些方法从头部和尾部实体的直接邻居中学习实体对表示,然后汇总参考实体对的表示。但是,只有从直接邻居那里学到的实体对代表可能具有较低的表现力,当参与实体稀疏直接邻居或与其他实体共享一个共同的当地社区。此外,仅仅对头部和尾部实体的语义信息进行建模不足以准确推断其关系信息,尤其是当它们具有多个关系时。为了解决这些问题,我们提出了一个特定于关系的上下文学习(RSCL)框架,该框架利用了三元组的图形上下文,以学习全球和本地关系特定的表示形式,以使其几乎没有相关关系。具体而言,我们首先提取每个三倍的图形上下文,这可以提供长期实体关系依赖性。为了编码提取的图形上下文,我们提出了一个分层注意网络,以捕获三元组的上下文信息并突出显示实体的有价值的本地邻里信息。最后,我们设计了一个混合注意聚合器,以评估全球和本地级别的查询三元组的可能性。两个公共数据集的实验结果表明,RSCL的表现优于最先进的FKGC方法。
translated by 谷歌翻译
随着未来以数据为中心的决策,对数据库的无缝访问至关重要。关于创建有效的文本到SQL(Text2SQL)模型以访问数据库的数据有广泛的研究。使用自然语言是可以通过有效访问数据库(尤其是对于非技术用户)来弥合数据和结果之间差距的最佳接口之一。它将打开门,并在精通技术技能或不太熟练的查询语言的用户中引起极大的兴趣。即使提出或研究了许多基于深度学习的算法,在现实工作场景中使用自然语言来解决数据查询问题仍然非常具有挑战性。原因是在不同的研究中使用不同的数据集,这带来了其局限性和假设。同时,我们确实缺乏对这些提议的模型及其对其训练的特定数据集的局限性的彻底理解。在本文中,我们试图介绍过去几年研究的24种神经网络模型的整体概述,包括其涉及卷积神经网络,经常性神经网络,指针网络,强化学习,生成模型等的架构。我们还概述11个数据集,这些数据集被广泛用于训练Text2SQL技术的模型。我们还讨论了无缝数据查询中文本2SQL技术的未来应用可能性。
translated by 谷歌翻译
Many machine learning tasks such as multiple instance learning, 3D shape recognition and fewshot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set, models used to address them should be permutation invariant. We present an attention-based neural network module, the Set Transformer, specifically designed to model interactions among elements in the input set. The model consists of an encoder and a decoder, both of which rely on attention mechanisms. In an effort to reduce computational complexity, we introduce an attention scheme inspired by inducing point methods from sparse Gaussian process literature. It reduces computation time of self-attention from quadratic to linear in the number of elements in the set. We show that our model is theoretically attractive and we evaluate it on a range of tasks, demonstrating increased performance compared to recent methods for set-structured data.
translated by 谷歌翻译
最近公布的知识图形嵌入模型的实施,培训和评估的异质性已经公平和彻底的比较困难。为了评估先前公布的结果的再现性,我们在Pykeen软件包中重新实施和评估了21个交互模型。在这里,我们概述了哪些结果可以通过其报告的超参数再现,这只能以备用的超参数再现,并且无法再现,并且可以提供洞察力,以及为什么会有这种情况。然后,我们在四个数据集上进行了大规模的基准测试,其中数千个实验和24,804 GPU的计算时间。我们展示了最佳实践,每个模型的最佳配置以及可以通过先前发布的最佳配置进行改进的洞察。我们的结果强调了模型架构,训练方法,丢失功能和逆关系显式建模的组合对于模型的性能来说至关重要,而不仅由模型架构决定。我们提供了证据表明,在仔细配置时,若干架构可以获得对最先进的结果。我们制定了所有代码,实验配置,结果和分析,导致我们在https://github.com/pykeen/pykeen和https://github.com/pykeen/benchmarking中获得的解释
translated by 谷歌翻译
我们设计了一个用户友好且可扩展的知识图构建(KGC)系统,用于从非结构化语料库中提取结构化知识。与现有的KGC系统不同,Gbuilder提供了一种灵活且用户定义的管道,可以包含IE模型的快速开发。可以使用更多基于内置的模板或启发式操作员和可编程操作员来适应来自不同域的数据。此外,我们还为Gbuilder设计了基于云的自适应任务计划,以确保其在大规模知识图构造上的可扩展性。实验评估不仅证明了Gbuilder在统一平台中组织多个信息提取模型的能力,还证实了其在大规模KGC任务上的高可扩展性。
translated by 谷歌翻译
事实证明,信息提取方法可有效从结构化或非结构化数据中提取三重。以(头部实体,关系,尾部实体)形式组织这样的三元组的组织称为知识图(kgs)。当前的大多数知识图都是不完整的。为了在下游任务中使用kgs,希望预测kgs中缺少链接。最近,通过将实体和关系嵌入到低维的矢量空间中,旨在根据先前访问的三元组来预测三元组,从而对KGS表示不同的方法。根据如何独立或依赖对三元组进行处理,我们将知识图完成的任务分为传统和图形神经网络表示学习,并更详细地讨论它们。在传统的方法中,每个三重三倍将独立处理,并在基于GNN的方法中进行处理,三倍也考虑了他们的当地社区。查看全文
translated by 谷歌翻译
内核选择在确定高斯过程(GP)模型中的性能方面发挥着核心作用,因为所选择的内核在之前的GP下确定了电感偏差和在GP下的功能的先前支持。这项工作解决了为高维GP回归模型构建自定义内核功能的挑战。从最近的深度学习进步中汲取灵感,我们介绍了一个名为Kitt的新方法:通过变压器识别内核识别。 KITT利用基于变压器的架构,以在0.1秒内生成内核建议,这比传统的内核搜索算法快几个数量级。我们使用从已知内核的词汇表中从前线生成的合成数据训练我们的模型。通过利用自我关注机制的性质,KITT能够处理具有任意尺寸的输入的数据集。我们证明,KITT选择的内核会在各种回归基准集合中产生强烈的表现。
translated by 谷歌翻译
即使机器学习算法已经在数据科学中发挥了重要作用,但许多当前方法对输入数据提出了不现实的假设。由于不兼容的数据格式,或数据集中的异质,分层或完全缺少的数据片段,因此很难应用此类方法。作为解决方案,我们提出了一个用于样本表示,模型定义和培训的多功能,统一的框架,称为“ Hmill”。我们深入审查框架构建和扩展的机器学习的多个范围范式。从理论上讲,为HMILL的关键组件的设计合理,我们将通用近似定理的扩展显示到框架中实现的模型所实现的所有功能的集合。本文还包含有关我们实施中技术和绩效改进的详细讨论,该讨论将在MIT许可下发布供下载。该框架的主要资产是其灵活性,它可以通过相同的工具对不同的现实世界数据源进行建模。除了单独观察到每个对象的一组属性的标准设置外,我们解释了如何在框架中实现表示整个对象系统的图表中的消息推断。为了支持我们的主张,我们使用框架解决了网络安全域的三个不同问题。第一种用例涉及来自原始网络观察结果的IoT设备识别。在第二个问题中,我们研究了如何使用以有向图表示的操作系统的快照可以对恶意二进制文件进行分类。最后提供的示例是通过网络中实体之间建模域黑名单扩展的任务。在所有三个问题中,基于建议的框架的解决方案可实现与专业方法相当的性能。
translated by 谷歌翻译
Deep Learning and Machine Learning based models have become extremely popular in text processing and information retrieval. However, the non-linear structures present inside the networks make these models largely inscrutable. A significant body of research has focused on increasing the transparency of these models. This article provides a broad overview of research on the explainability and interpretability of natural language processing and information retrieval methods. More specifically, we survey approaches that have been applied to explain word embeddings, sequence modeling, attention modules, transformers, BERT, and document ranking. The concluding section suggests some possible directions for future research on this topic.
translated by 谷歌翻译
Scene graph generation from images is a task of great interest to applications such as robotics, because graphs are the main way to represent knowledge about the world and regulate human-robot interactions in tasks such as Visual Question Answering (VQA). Unfortunately, its corresponding area of machine learning is still relatively in its infancy, and the solutions currently offered do not specialize well in concrete usage scenarios. Specifically, they do not take existing "expert" knowledge about the domain world into account; and that might indeed be necessary in order to provide the level of reliability demanded by the use case scenarios. In this paper, we propose an initial approximation to a framework called Ontology-Guided Scene Graph Generation (OG-SGG), that can improve the performance of an existing machine learning based scene graph generator using prior knowledge supplied in the form of an ontology (specifically, using the axioms defined within); and we present results evaluated on a specific scenario founded in telepresence robotics. These results show quantitative and qualitative improvements in the generated scene graphs.
translated by 谷歌翻译
In the past few years, neural architecture search (NAS) has become an increasingly important tool within the deep learning community. Despite the many recent successes of NAS, however, most existing approaches operate within highly structured design spaces, and hence explore only a small fraction of the full search space of neural architectures while also requiring significant manual effort from domain experts. In this work, we develop techniques that enable efficient NAS in a significantly larger design space. To accomplish this, we propose to perform NAS in an abstract search space of program properties. Our key insights are as follows: (1) the abstract search space is significantly smaller than the original search space, and (2) architectures with similar program properties also have similar performance; thus, we can search more efficiently in the abstract search space. To enable this approach, we also propose a novel efficient synthesis procedure, which accepts a set of promising program properties, and returns a satisfying neural architecture. We implement our approach, $\alpha$NAS, within an evolutionary framework, where the mutations are guided by the program properties. Starting with a ResNet-34 model, $\alpha$NAS produces a model with slightly improved accuracy on CIFAR-10 but 96% fewer parameters. On ImageNet, $\alpha$NAS is able to improve over Vision Transformer (30% fewer FLOPS and parameters), ResNet-50 (23% fewer FLOPS, 14% fewer parameters), and EfficientNet (7% fewer FLOPS and parameters) without any degradation in accuracy.
translated by 谷歌翻译
The development of deep neural networks has improved representation learning in various domains, including textual, graph structural, and relational triple representations. This development opened the door to new relation extraction beyond the traditional text-oriented relation extraction. However, research on the effectiveness of considering multiple heterogeneous domain information simultaneously is still under exploration, and if a model can take an advantage of integrating heterogeneous information, it is expected to exhibit a significant contribution to many problems in the world. This thesis works on Drug-Drug Interactions (DDIs) from the literature as a case study and realizes relation extraction utilizing heterogeneous domain information. First, a deep neural relation extraction model is prepared and its attention mechanism is analyzed. Next, a method to combine the drug molecular structure information and drug description information to the input sentence information is proposed, and the effectiveness of utilizing drug molecular structures and drug descriptions for the relation extraction task is shown. Then, in order to further exploit the heterogeneous information, drug-related items, such as protein entries, medical terms and pathways are collected from multiple existing databases and a new data set in the form of a knowledge graph (KG) is constructed. A link prediction task on the constructed data set is conducted to obtain embedding representations of drugs that contain the heterogeneous domain information. Finally, a method that integrates the input sentence information and the heterogeneous KG information is proposed. The proposed model is trained and evaluated on a widely used data set, and as a result, it is shown that utilizing heterogeneous domain information significantly improves the performance of relation extraction from the literature.
translated by 谷歌翻译