捕获该段落中的单词中复杂语言结构和长期依赖性的能力对于话语级关系提取(DRE)任务是必不可少的。图形神经网络(GNNS)是编码依赖图的方法之一,它在先前的RE中有效地显示了。然而,对GNN的接受领域得到了相对较少的关注,这对于需要话语理解的非常长的文本的情况可能是至关重要的。在这项工作中,我们利用图形汇集的想法,并建议在DRE任务上使用汇集解凝框架。汇集分支减少了图形尺寸,使GNN能够在更少的层内获得更大的接收领域; UnoDooling分支将池化图恢复为其原始分辨率,以便可以提取实体提及的表示。我们提出子句匹配(cm),这是一个新的语言启发图形汇集方法,用于NLP任务。两个DE DATASET上的实验表明,我们的模型在需要建模长期依赖性时显着改善基线,这表明了汇集了解冻框架的有效性和我们的CM汇集方法。
translated by 谷歌翻译
文档级关系提取(DRE)旨在识别两个实体之间的关系。实体可以对应于超越句子边界的多个提升。以前很少有研究已经调查了提及集成,这可能是有问题的,因为库鲁弗提到对特定关系没有同样有贡献。此外,事先努力主要关注实体级的推理,而不是捕获实体对之间的全局相互作用。在本文中,我们提出了两种新颖的技术,上下文指导的集成和交互推理(CGM2IR),以改善DRE。而不是简单地应用平均池,而是利用上下文来指导在加权和方式中的经验提升的集成。另外,对实体对图的相互作用推理在实体对图上执行迭代算法,以模拟关系的相互依赖性。我们在三个广泛使用的基准数据集中评估我们的CGM2IR模型,即Docred,CDR和GDA。实验结果表明,我们的模型优于以前的最先进的模型。
translated by 谷歌翻译
Open Information Extraction (OpenIE) aims to extract relational tuples from open-domain sentences. Traditional rule-based or statistical models have been developed based on syntactic structures of sentences, identified by syntactic parsers. However, previous neural OpenIE models under-explore the useful syntactic information. In this paper, we model both constituency and dependency trees into word-level graphs, and enable neural OpenIE to learn from the syntactic structures. To better fuse heterogeneous information from both graphs, we adopt multi-view learning to capture multiple relationships from them. Finally, the finetuned constituency and dependency representations are aggregated with sentential semantic representations for tuple generation. Experiments show that both constituency and dependency information, and the multi-view learning are effective.
translated by 谷歌翻译
医疗关系提取(MRE)任务旨在提取医学文本中实体之间的关系。传统的关系提取方法通过探索句法信息,例如依赖树。但是,由外域解析器产生的医学文本的1好的依赖树的质量相对有限,因此医疗关系提取方法的性能可能会退化。为此,我们提出了一种基于因果解释理论的医学文本中共同模拟语义和句法信息的方法。我们生成依赖性森林,这些森林由1-最佳依赖树组成。然后,采用特定于任务的因果解释者来修剪依赖性森林,该森林将进一步送入设计的图形卷积网络,以学习下游任务的相应表示。从经验上讲,基准医学数据集的各种比较证明了我们模型的有效性。
translated by 谷歌翻译
Document-level relation extraction (DocRE) aims to identify semantic labels among entities within a single document. One major challenge of DocRE is to dig decisive details regarding a specific entity pair from long text. However, in many cases, only a fraction of text carries required information, even in the manually labeled supporting evidence. To better capture and exploit instructive information, we propose a novel expLicit syntAx Refinement and Subsentence mOdeliNg based framework (LARSON). By introducing extra syntactic information, LARSON can model subsentences of arbitrary granularity and efficiently screen instructive ones. Moreover, we incorporate refined syntax into text representations which further improves the performance of LARSON. Experimental results on three benchmark datasets (DocRED, CDR, and GDA) demonstrate that LARSON significantly outperforms existing methods.
translated by 谷歌翻译
文本分类任务的关键是语言表示和重要信息提取,并且有许多相关研究。近年来,文本分类中的图形神经网络(GNN)的研究逐渐出现并显示出其优势,但现有模型主要集中于直接将单词作为图形节点直接输入GNN模型,而忽略了不同级别的语义结构信息。样品。为了解决该问题,我们提出了一个新的层次图神经网络(HIEGNN),该图分别从Word级,句子级别和文档级别提取相应的信息。与几种基线方法相比,几个基准数据集的实验结果取得更好或相似的结果,这表明我们的模型能够从样品中获得更多有用的信息。
translated by 谷歌翻译
增强图在正规化图形神经网络(GNNS)方面起着至关重要的作用,该图形以信息传递的形式利用沿图的边缘进行信息交换。由于其有效性,简单的边缘和节点操作(例如,添加和删除)已被广泛用于图表增强中。然而,这种常见的增强技术可以显着改变原始图的语义,从而导致过度侵略性增强,从而在GNN学习中拟合不足。为了解决掉落或添加图形边缘和节点引起的此问题,我们提出了SoftEdge,将随机权重分配给给定图的一部分以进行增强。 SoftEdge生成的合成图保持与原始图相同的节点及其连接性,从而减轻原始图的语义变化。我们从经验上表明,这种简单的方法获得了与流行节点和边缘操纵方法的卓越精度,并且具有明显的弹性,可抵御GNN深度的准确性降解。
translated by 谷歌翻译
考虑到RDF三元组的集合,RDF到文本生成任务旨在生成文本描述。最先前的方法使用序列到序列模型或使用基于图形的模型来求解此任务以编码RDF三维并生成文本序列。然而,这些方法未能明确模拟RDF三元组之间的本地和全球结构信息。此外,以前的方法也面临了生成文本的低信任问题的不可忽略的问题,这严重影响了这些模型的整体性能。为了解决这些问题,我们提出了一种组合两个新的图形增强结构神经编码器的模型,共同学习输入的RDF三元组中的本地和全局结构信息。为了进一步改进文本忠诚,我们创新地根据信息提取(即)引进了强化学习(RL)奖励。我们首先使用佩带的IE模型从所生成的文本中提取三元组,并将提取的三级的正确数量视为额外的RL奖励。两个基准数据集上的实验结果表明,我们所提出的模型优于最先进的基线,额外的加强学习奖励确实有助于改善所生成的文本的忠诚度。
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
在非欧几里得空间上卷积成功之后,在有关图形的各种任务上也验证了相应的合并方法。但是,由于固定的压缩配额和逐步合并设计,这些层次池方法仍然遭受局部结构损害和次优问题的困扰。在这项工作的启发下,我们提出了一种层次的合并方法,即SEP解决这两个问题。具体而言,在不分配特定层的压缩配额的情况下,全局优化算法旨在生成一次集群分配矩阵以一次汇总。然后,我们介绍了在环和网格合成图的重建中先前方法中局部结构损害的例证。除SEP外,我​​们还将分别设计两个分类模型,分别用于图形分类和节点分类。结果表明,SEP在图形分类基准上优于最先进的图形合并方法,并在节点分类上获得了卓越的性能。
translated by 谷歌翻译
最近,图形神经网络(GNNS)大大提高了图形分类的任务。通常,我们首先在给定的训练集中使用图形构建一个统一的GNN模型,然后使用该统一模型来预测测试集中所有看不见图的标签。然而,相同数据集中的图形通常具有显着的结构,这表明统一模型可以给定单独的图形。因此,在本文中,我们的目标是开发用于图形分类的定制图形神经网络。具体而言,我们提出了一种新颖的定制图形神经网络框架,即定制-GNN。鉴于图表样本,定制-GNN可以基于其结构为该图产生特定于样的模型。同时,所提出的框架非常一般,可以应用于许多现有图形神经网络模型。各种图形分类基准的综合实验证明了拟议框架的有效性。
translated by 谷歌翻译
文本分类是自然语言处理(NLP)的主要任务。最近,图神经网络(GNN)已迅速发展,并应用于文本分类任务。作为一种特殊的图形数据,该树具有更简单的数据结构,可以为文本分类提供丰富的层次结构信息。受结构熵的启发,我们通过最小化结构熵并提出提示来构造图形的编码树,该提示旨在充分利用文本中包含的文本中包含的层次信息,以完成文本分类的任务。具体来说,我们首先为每个文本建立依赖关系解析图。然后,我们设计了一种结构熵最小化算法来解码图中的关键信息,并将每个图转换为其相应的编码树。基于编码树的层次结构,通过逐层更新编码树中的非叶子节点的表示来获得整个图的表示。最后,我们介绍了层次信息在文本分类中的有效性。实验结果表明,在具有简单的结构和很少的参数的同时,提示在流行基准测试上的最新方法优于最先进的方法。
translated by 谷歌翻译
Machine reading comprehension (MRC) is a long-standing topic in natural language processing (NLP). The MRC task aims to answer a question based on the given context. Recently studies focus on multi-hop MRC which is a more challenging extension of MRC, which to answer a question some disjoint pieces of information across the context are required. Due to the complexity and importance of multi-hop MRC, a large number of studies have been focused on this topic in recent years, therefore, it is necessary and worth reviewing the related literature. This study aims to investigate recent advances in the multi-hop MRC approaches based on 31 studies from 2018 to 2022. In this regard, first, the multi-hop MRC problem definition will be introduced, then 31 models will be reviewed in detail with a strong focus on their multi-hop aspects. They also will be categorized based on their main techniques. Finally, a fine-grain comprehensive comparison of the models and techniques will be presented.
translated by 谷歌翻译
最近,图形神经网络(GNNS)在各种现实情景中获得了普及。尽管取得了巨大成功,但GNN的建筑设计严重依赖于体力劳动。因此,自动化图形神经网络(Autopmn)引起了研究界的兴趣和关注,近年来显着改善。然而,现有的autopnn工作主要采用隐式方式来模拟并利用图中的链接信息,这对图中的链路预测任务不充分规范化,并限制了自动启动的其他图表任务。在本文中,我们介绍了一个新的Autognn工作,该工作明确地模拟了缩写为autogel的链接信息。以这种方式,AutoGel可以处理链路预测任务并提高Autognns对节点分类和图形分类任务的性能。具体地,AutoGel提出了一种新的搜索空间,包括层内和层间设计中的各种设计尺寸,并采用更强大的可分辨率搜索算法,以进一步提高效率和有效性。基准数据集的实验结果展示了自动池上的优势在几个任务中。
translated by 谷歌翻译
Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders, and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes, benchmark data sets, and model evaluation of graph neural networks. Finally, we propose potential research directions in this rapidly growing field.
translated by 谷歌翻译
文档级别的关系提取旨在提取文档中实体之间的关系。与其句子级的对应物相比,文档级关系提取需要对多个句子进行推断才能提取复杂的关系三元组。先前的研究通常通过有关提及级别或实体级文档编写的信息传播来完成推理,而与关系之间的相关性无关。在本文中,我们提出了一个基于掩盖图像重建网络(DRE-MIR)的新型文档级关系提取模型,该模型将推断模型为掩盖的图像重建问题,以捕获关系之间的相关性。具体来说,我们首先利用编码器模块来获取实体的功能,并根据功能构建实体对矩阵。之后,我们将实体对矩阵视为图像,然后随机掩盖它并通过推理模块恢复它以捕获关系之间的相关性。我们在三个公共文档级关系提取数据集(即Docred,CDR和GDA)上评估了我们的模型。实验结果表明,我们的模型在这三个数据集上实现了最先进的性能,并且在推理过程中对噪声具有出色的鲁棒性。
translated by 谷歌翻译
意义表示(AMR)是一种基于图形的语义表示的句子,由语义关系链接的概念集合组成。基于AMR的方法在各种应用程序中找到了成功,但在需要文档级背景下的任务中使用它的挑战是它只代表单个句子。在基于AMR的总结中的事先工作已经自动将单个句子图与文档图合并到文档图中,但尚未独立地评估合并方法及其对摘要内容选择的影响。在本文中,我们介绍了一种新的数据集,由配对文件的节点与可用于评估(1)合并策略之间的摘要之间的人为注释对齐组成; (2)在合并或未混合的AMR图表的节点上的内容选择方法的性能。我们将这两种形式的评估应用于现有工作以及节点合并的新方法,并表明我们的新方法比现有工作明显更好。
translated by 谷歌翻译
我们为图神经网络提供了一种通用和趋势感知的课程学习方法。它通过结合样品级别的损失趋势来扩展现有方法,以更好地区分更轻松的样本并安排培训。该模型有效地集成了文本和结构信息,以在文本图中提取关系提取。实验结果表明,该模型提供了对样品难度的强大估计,并显示了几个数据集对最新方法的显着改善。
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
Text classification is an important and classical problem in natural language processing. There have been a number of studies that applied convolutional neural networks (convolution on regular grid, e.g., sequence) to classification. However, only a limited number of studies have explored the more flexible graph convolutional neural networks (convolution on non-grid, e.g., arbitrary graph) for the task. In this work, we propose to use graph convolutional networks for text classification. We build a single text graph for a corpus based on word co-occurrence and document word relations, then learn a Text Graph Convolutional Network (Text GCN) for the corpus. Our Text GCN is initialized with one-hot representation for word and document, it then jointly learns the embeddings for both words and documents, as supervised by the known class labels for documents. Our experimental results on multiple benchmark datasets demonstrate that a vanilla Text GCN without any external word embeddings or knowledge outperforms state-of-the-art methods for text classification. On the other hand, Text GCN also learns predictive word and document embeddings. In addition, experimental results show that the improvement of Text GCN over state-of-the-art comparison methods become more prominent as we lower the percentage of training data, suggesting the robustness of Text GCN to less training data in text classification.
translated by 谷歌翻译