在本文中,我们提出了多跳问题回答的两个阶段模型。第一阶段是一个层次图网络,该网络用于对多跳问题进行推理,并能够使用文档的自然结构(即段落,问题,句子和实体)捕获不同级别的粒度。推理过程是转换为节点分类任务(即,段落节点和句子节点)。第二阶段是语言模型微调任务。在一句话中,第一阶段使用图形神经网络选择和连接支持句子作为一个段落,第二阶段在语言模型微调范式中找到答案跨度。
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
近年来,在挑战的多跳QA任务方面有令人印象深刻的进步。然而,当面对输入文本中的一些干扰时,这些QA模型可能会失败,并且它们进行多跳推理的可解释性仍然不确定。以前的逆势攻击作品通常编辑整个问题句,这对测试基于实体的多跳推理能力有限。在本文中,我们提出了一种基于多跳推理链的逆势攻击方法。我们将从查询实体开始的多跳推理链与构造的图表中的答案实体一起制定,这使我们能够将问题对齐到每个推理跳跃,从而攻击任何跃点。我们将问题分类为不同的推理类型和对应于所选推理跳的部分问题,以产生分散注意力的句子。我们在HotpotQA DataSet上的三个QA模型上测试我们的对抗方案。结果表明,对答案和支持事实预测的显着性能降低,验证了我们推理基于链条推理模型的攻击方法的有效性以及它们的脆弱性。我们的对抗重新培训进一步提高了这些模型的性能和鲁棒性。
translated by 谷歌翻译
现有的kg增强模型用于问题回答主要专注于设计精心图形神经网络(GNN)以模拟知识图(KG)。但是,它们忽略了(i)有效地融合和推理过问题上下文表示和kg表示,并且(ii)在推理期间自动从嘈杂的KG中选择相关节点。在本文中,我们提出了一种新颖的型号,其通过LMS和GNN的联合推理和动态KGS修剪机制解决了上述限制。具体而言,ConntLK通过新的密集双向注意模块在LMS和GNN之间执行联合推理,其中每个问题令牌参加KG节点,每个KG节点都会参加问题令牌,并且两个模态表示熔断和通过多次熔断和更新。步互动。然后,动态修剪模块使用通过联合推理产生的注意重量来递归修剪无关的kg节点。我们在CommanSENSEQA和OpenBookQA数据集上的结果表明,我们的模态融合和知识修剪方法可以更好地利用相关知识来推理。
translated by 谷歌翻译
多跳的推理需要汇总多个文档来回答一个复杂的问题。现有方法通常将多跳问题分解为更简单的单跳问题,以解决说明可解释的推理过程的问题。但是,他们忽略了每个推理步骤的支持事实的基础,这往往会产生不准确的分解。在本文中,我们提出了一个可解释的逐步推理框架,以在每个中间步骤中同时合并单跳支持句子识别和单跳问题生成,并利用当前跳跃的推断,直到推理最终结果。我们采用统一的读者模型来进行中级跳跃推理和最终的跳跃推理,并采用关节优化,以更准确,强大的多跳上推理。我们在两个基准数据集HOTPOTQA和2WIKIMULTIHOPQA上进行实验。结果表明,我们的方法可以有效地提高性能,并在不分解监督的情况下产生更好的解释推理过程。
translated by 谷歌翻译
Multi-hop machine reading comprehension is a challenging task in natural language processing, which requires more reasoning ability across multiple documents. Spectral models based on graph convolutional networks grant inferring abilities and lead to competitive results. However, part of them still faces the challenge of analyzing the reasoning in a human-understandable way. Inspired by the concept of the Grandmother Cells in cognitive neuroscience, a spatial graph attention framework named ClueReader was proposed in this paper, imitating the procedure. This model is designed to assemble the semantic features in multi-level representations and automatically concentrate or alleviate information for reasoning via the attention mechanism. The name ClueReader is a metaphor for the pattern of the model: regard the subjects of queries as the start points of clues, take the reasoning entities as bridge points, consider the latent candidate entities as the grandmother cells, and the clues end up in candidate entities. The proposed model allows us to visualize the reasoning graph, then analyze the importance of edges connecting two entities and the selectivity in the mention and candidate nodes, which can be easier to be comprehended empirically. The official evaluations in the open-domain multi-hop reading dataset WikiHop and the Drug-drug Interactions dataset MedHop prove the validity of our approach and show the probability of the application of the model in the molecular biology domain.
translated by 谷歌翻译
多跳问题回答(QA)需要对多个文档进行推理,以回答一个复杂的问题并提供可解释的支持证据。但是,提供支持证据不足以证明模型已经执行了所需的推理来达到正确的答案。大多数现有的多跳质量检查方法也无法回答大部分子问题,即使他们的父母问题得到了正确的回答。在本文中,我们为多跳QA提出了基于及时的保护学习(PCL)框架,该框架从多跳QA任务中获取了新知识,同时保留了在单跳QA任务上学习的旧知识,从而减轻了遗忘。具体来说,我们首先在现有的单跳质量检查任务上训练模型,然后冻结该模型,并通过为多跳质量检查任务分配其他子网络来扩展它。此外,为了调整预训练的语言模型以刺激特定多跳问题所需的推理类型,我们学习了新型子网络的软提示,以执行特定于类型的推理。 HOTPOTQA基准测试的实验结果表明,PCL具有多跳质量质量质量检查的竞争力,并且在相应的单跳子问题上保留了良好的性能,这表明PCL通过忘记通过忘记来减轻知识丧失的功效。
translated by 谷歌翻译
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a;Radford et al., 2018), BERT is designed to pretrain deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be finetuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial taskspecific architecture modifications.BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).
translated by 谷歌翻译
使用从预先接受训练的语言模型(LMS)和知识图表(LMS)和知识图表(kgs)回答问题的问题提出了两个挑战:给定QA上下文(问答选择),方法需要(i)从大型千克识别相关知识,(ii)对QA上下文和kg进行联合推理。在这项工作中,我们提出了一种新的模型,QA-GNN,它通过两个关键创新解决了上述挑战:(i)相关评分,我们使用LMS来估计KG节点相对于给定的QA上下文的重要性,以及(ii)联合推理,我们将QA上下文和kg连接到联合图,并通过图形神经网络相互更新它们的表示。我们评估了QA基准的模型(CommanSeaseQA,OpenBookQA)和生物医学(MedQa-USMLE)域名。QA-GNN优于现有的LM和LM + kg模型,并表现出可解释和结构化推理的能力,例如,正确处理问题的否定。
translated by 谷歌翻译
Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers. We introduce HOTPOTQA, a new dataset with 113k Wikipedia-based question-answer pairs with four key features: (1) the questions require finding and reasoning over multiple supporting documents to answer; (2) the questions are diverse and not constrained to any pre-existing knowledge bases or knowledge schemas; (3) we provide sentence-level supporting facts required for reasoning, allowing QA systems to reason with strong supervision and explain the predictions; (4) we offer a new type of factoid comparison questions to test QA systems' ability to extract relevant facts and perform necessary comparison. We show that HOTPOTQA is challenging for the latest QA systems, and the supporting facts enable models to improve performance and make explainable predictions.
translated by 谷歌翻译
这项工作调查了以知识图(kg)形式的外部知识来源的理解问题的学习和推理的挑战。我们提出了一种新型的图形神经网络体系结构,称为动态相关图形网络(DRGN)。 DRGN根据问题和答案实体在给定的KG子图上运行,并使用节点之间的相关得分来动态建立新的边缘,以在图形网络中学习节点表示。相关性的这种显式用法作为图表具有以下优点,a)模型可以利用现有关系,重新缩放节点权重,并影响邻里节点的表示方式在kg子图中汇总的方式,b)恢复推理所需的千克中缺失的边缘。此外,作为副产品,由于考虑了问题节点与图形实体之间的相关性,我们的模型改善了处理负面问题。与最新发布的结果相比,我们提出的方法在两个质量检查基准CommonSenseQA和OpenBookQA上显示了竞争性能。
translated by 谷歌翻译
问题答案(QA)是自然语言处理中最具挑战性的最具挑战性的问题之一(NLP)。问答(QA)系统试图为给定问题产生答案。这些答案可以从非结构化或结构化文本生成。因此,QA被认为是可以用于评估文本了解系统的重要研究区域。大量的QA研究致力于英语语言,调查最先进的技术和实现最先进的结果。然而,由于阿拉伯QA中的研究努力和缺乏大型基准数据集,在阿拉伯语问答进展中的研究努力得到了很大速度的速度。最近许多预先接受的语言模型在许多阿拉伯语NLP问题中提供了高性能。在这项工作中,我们使用四个阅读理解数据集来评估阿拉伯QA的最先进的接种变压器模型,它是阿拉伯语 - 队,ArcD,AQAD和TYDIQA-GoldP数据集。我们微调并比较了Arabertv2基础模型,ArabertV0.2大型型号和ARAElectra模型的性能。在最后,我们提供了一个分析,了解和解释某些型号获得的低绩效结果。
translated by 谷歌翻译
预训练的语言模型(PLM)在各种自然语言理解任务上取得了巨大的成功。另一方面,对PLM的简单微调对于特定于领域的任务可能是次优的,因为它们不可能涵盖所有域中的知识。尽管PLM的自适应预培训可以帮助他们获得特定于领域的知识,但需要大量的培训成本。此外,自适应预训练可能会通过造成灾难性忘记其常识来损害PLM在下游任务上的表现。为了克服PLM适应性适应性预训练的这种局限性,我们提出了一个新颖的域名适应框架,用于将PLMS创造为知识增强语言模型适应性(KALA),该框架调节了PLM的中间隐藏表示与域中的中间隐藏表示,由实体和实体和实体和实体和实体构成他们的关系事实。我们验证了Kala在问题答案中的性能,并在各个域的多个数据集上命名实体识别任务。结果表明,尽管在计算上有效,但我们的Kala在很大程度上优于适应性预训练。代码可在以下网址获得:https://github.com/nardien/kala/。
translated by 谷歌翻译
Question Answering (QA) is a task that entails reasoning over natural language contexts, and many relevant works augment language models (LMs) with graph neural networks (GNNs) to encode the Knowledge Graph (KG) information. However, most existing GNN-based modules for QA do not take advantage of rich relational information of KGs and depend on limited information interaction between the LM and the KG. To address these issues, we propose Question Answering Transformer (QAT), which is designed to jointly reason over language and graphs with respect to entity relations in a unified manner. Specifically, QAT constructs Meta-Path tokens, which learn relation-centric embeddings based on diverse structural and semantic relations. Then, our Relation-Aware Self-Attention module comprehensively integrates different modalities via the Cross-Modal Relative Position Bias, which guides information exchange between relevant entities of different modalities. We validate the effectiveness of QAT on commonsense question answering datasets like CommonsenseQA and OpenBookQA, and on a medical question answering dataset, MedQA-USMLE. On all the datasets, our method achieves state-of-the-art performance. Our code is available at http://github.com/mlvlab/QAT.
translated by 谷歌翻译
大多数阅读理解的研究都集中在基于单个文档甚至单一段落的问题上回答问题。我们介绍了一个神经模型,该神经模型集成和理由依赖于文档中和跨多个文档中的信息传播。我们将其作为图表上的推理问题构图。提及实体是该图的节点,而边缘编码不同提及(例如,内部和跨文档的共同参考)之间的关系。图形卷积网络(GCN)应用于这些图形,并经过训练以执行多步电推理。我们的实体-GCN方法是可扩展的,紧凑的,它可以在答案数据集的多文件问题上获得最新的结果,Wikihop(Welbl等,2018)。
translated by 谷歌翻译
Label smoothing is a regularization technique widely used in supervised learning to improve the generalization of models on various tasks, such as image classification and machine translation. However, the effectiveness of label smoothing in multi-hop question answering (MHQA) has yet to be well studied. In this paper, we systematically analyze the role of label smoothing on various modules of MHQA and propose F1 smoothing, a novel label smoothing technique specifically designed for machine reading comprehension (MRC) tasks. We evaluate our method on the HotpotQA dataset and demonstrate its superiority over several strong baselines, including models that utilize complex attention mechanisms. Our results suggest that label smoothing can be effective in MHQA, but the choice of smoothing strategy can significantly affect performance.
translated by 谷歌翻译
文本逻辑推理,尤其是具有逻辑推理的问题答案(QA)任务,需要对特定逻辑结构的认识。段落级别的逻辑关系代表了命题单位之间的必要或矛盾(例如,结论性句子)。但是,由于当前的质量检查系统专注于基于实体的关系,因此无法探索此类结构。在这项工作中,我们提出了逻辑结构构成建模,以解决逻辑推理质量质量质量质量质量质量质量质量质量质量质量质量质量质量质量质量质量质量质量质量质量质量质量质量质量请参见。网络执行两个过程:(1)利用在线话语连接以及通用逻辑理论的逻辑图构造,(2)通过图形网络学习产生结构性逻辑特征的逻辑表示。该管道应用于一般编码器,其基本功能与高级逻辑功能相结合,以进行答案预测。在三个文本逻辑推理数据集上进行的实验证明了dagns内置的逻辑结构的合理性以及学到的逻辑特征的有效性。此外,零射传输结果显示了特征的通用性,可看不见的逻辑文本。
translated by 谷歌翻译
在开放的书本回答(OBQA)任务中,从分散注意力的信息中选择相关段落和句子对于推理问题的答案至关重要。 HOTPOTQA数据集旨在教授和评估系统以进行段落排名和句子选择。许多现有框架使用单独的模型分别选择相关段落和句子。这样的系统不仅在模型的参数方面具有很高的复杂性,而且还无法将训练这两个任务训练在一起的优势,因为一项任务可能对另一个任务有益。在这项工作中,我们提出了一个简单而有效的框架,可以通过共同排名段落和选择句子来解决这些限制。此外,我们提出一致性和相似性约束,以促进段落排名和句子选择之间的相关性和相互作用。实验表明,我们的框架可以与以前的系统实现竞争性结果,并就相关句子的确切匹配而优于28 \%在HOTPOTQA数据集上。
translated by 谷歌翻译
我们研究了学习因果推理对程序文本的挑战,以回答“如果...”何时需要外常识知识。我们提出了一个新颖的多跳图推理模型,以1)有效地从大知识图中提取常识子图;2)通过推理从常识子图获得的表示以及问题与上下文之间的上下文相互作用来预测因果答案。我们评估了WIQA基准测试的模型,并与最近的模型相比实现了最先进的性能。
translated by 谷歌翻译
Multi-hop Machine reading comprehension is a challenging task with aim of answering a question based on disjoint pieces of information across the different passages. The evaluation metrics and datasets are a vital part of multi-hop MRC because it is not possible to train and evaluate models without them, also, the proposed challenges by datasets often are an important motivation for improving the existing models. Due to increasing attention to this field, it is necessary and worth reviewing them in detail. This study aims to present a comprehensive survey on recent advances in multi-hop MRC evaluation metrics and datasets. In this regard, first, the multi-hop MRC problem definition will be presented, then the evaluation metrics based on their multi-hop aspect will be investigated. Also, 15 multi-hop datasets have been reviewed in detail from 2017 to 2022, and a comprehensive analysis has been prepared at the end. Finally, open issues in this field have been discussed.
translated by 谷歌翻译