随着自动假新闻检测技术的快速发展,事实提取和验证(发烧)吸引了更多的关注。该任务旨在从数百万个开放域Wikipedia文件中提取最相关的事实证据,然后验证相应索赔的可信度。尽管已经为该任务提出了几种强大的模型,但他们取得了长足的进步,但我们认为他们无法利用多视图上下文信息,因此无法获得更好的性能。在本文中,我们建议整合多视图上下文信息(IMCI)进行事实提取和验证。对于每个证据句子,我们定义两种上下文,即文档内部上下文和文档间的上下文}。文档内上下文由文档标题和同一文档中的所有其他句子组成。文档间的上下文包括所有其他证据,这些证据可能来自不同的文档。然后,我们集成了多视图上下文信息,以编码证据句子以处理任务。我们对发烧1.0共享任务的实验结果表明,我们的IMCI框架在事实提取和验证方面取得了长足的进步,并以72.97%的胜利发烧得分达到了最先进的表现,在线上获得了75.84%的标签准确度盲测。我们还进行消融研究以检测多视图上下文信息的影响。我们的代码将在https://github.com/phoenixsecularbird/imci上发布。
translated by 谷歌翻译
我们研究了检查问题的事实,旨在识别给定索赔的真实性。具体而言,我们专注于事实提取和验证(发烧)及其伴随数据集的任务。该任务包括从维基百科检索相关文件(和句子)并验证文件中的信息是否支持或驳斥所索赔的索赔。此任务至关重要,可以是假新闻检测和医疗索赔验证等应用程序块。在本文中,我们以通过以结构化和全面的方式呈现文献来更好地了解任务的挑战。我们通过分析不同方法的技术视角并讨论发热数据集的性能结果,描述了所提出的方法,这是最熟悉的和正式结构化的数据集,就是事实提取和验证任务。我们还迄今为止迄今为止确定句子检索组件的有益损失函数的最大实验研究。我们的分析表明,采样负句对于提高性能并降低计算复杂性很重要。最后,我们描述了开放的问题和未来的挑战,我们激励了未来的任务研究。
translated by 谷歌翻译
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
A key component of fact verification is thevevidence retrieval, often from multiple documents. Recent approaches use dense representations and condition the retrieval of each document on the previously retrieved ones. The latter step is performed over all the documents in the collection, requiring storing their dense representations in an index, thus incurring a high memory footprint. An alternative paradigm is retrieve-and-rerank, where documents are retrieved using methods such as BM25, their sentences are reranked, and further documents are retrieved conditioned on these sentences, reducing the memory requirements. However, such approaches can be brittle as they rely on heuristics and assume hyperlinks between documents. We propose a novel retrieve-and-rerank method for multi-hop retrieval, that consists of a retriever that jointly scores documents in the knowledge source and sentences from previously retrieved documents using an autoregressive formulation and is guided by a proof system based on natural logic that dynamically terminates the retrieval process if the evidence is deemed sufficient. This method is competitive with current state-of-the-art methods on FEVER, HoVer and FEVEROUS-S, while using $5$ to $10$ times less memory than competing systems. Evaluation on an adversarial dataset indicates improved stability of our approach compared to commonly deployed threshold-based methods. Finally, the proof system helps humans predict model decisions correctly more often than using the evidence alone.
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
现有的假新闻检测方法旨在将新闻分类为真或错误,并提供真实的解释,从而实现出色的表现。但是,他们经常根据有限的新闻报道和揭穿延误来定制手动事实检查报告的自动解决方案。如果尚未对一段新闻进行事实检查或揭穿事实,通常会在各种媒体上传播一定数量的相关原始报告,其中包含人群的智慧来验证新闻声明并解释其判决。在本文中,我们提出了一个新颖的粗到十五级别的级联证据依据(COFCED)神经网络,以根据此类原始报告来解释假新闻检测,从而减轻了对事实检查的依赖性。具体而言,我们首先使用层次结构编码器来用于Web文本表示,然后开发两个级联的选择器,以粗略至上的方式在所选的Top-K报告之上选择最可解释的句子。此外,我们构建了两个可解释的假新闻数据集,这些数据集可公开使用。实验结果表明,我们的模型显着优于最先进的基线,并从不同的评估角度产生高质量的解释。
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
Emotion-cause pair extraction (ECPE) aims to extract emotion clauses and corresponding cause clauses, which have recently received growing attention. Previous methods sequentially encode features with a specified order. They first encode the emotion and cause features for clause extraction and then combine them for pair extraction. This lead to an imbalance in inter-task feature interaction where features extracted later have no direct contact with the former. To address this issue, we propose a novel Pair-Based Joint Encoding (PBJE) network, which generates pairs and clauses features simultaneously in a joint feature encoding manner to model the causal relationship in clauses. PBJE can balance the information flow among emotion clauses, cause clauses and pairs. From a multi-relational perspective, we construct a heterogeneous undirected graph and apply the Relational Graph Convolutional Network (RGCN) to capture the various relationship between clauses and the relationship between pairs and clauses. Experimental results show that PBJE achieves state-of-the-art performance on the Chinese benchmark corpus.
translated by 谷歌翻译
多跳的推理(即跨两个或多个文档的推理)是NLP模型的关键要素,该模型利用大型语料库表现出广泛的知识。为了检索证据段落,多跳模型必须与整个啤酒花的快速增长的搜索空间抗衡,代表结合多个信息需求的复杂查询,并解决有关在训练段落之间跳出的最佳顺序的歧义。我们通过Baleen解决了这些问题,Baleen可以提高多跳检索的准确性,同时从多跳的训练信号中学习强大的训练信号的准确性。为了驯服搜索空间,我们提出了凝结的检索,该管道总结了每个跃点后检索到单个紧凑型上下文的管道。为了建模复杂的查询,我们引入了一个重点的后期相互作用检索器,该检索器允许同一查询表示的不同部分匹配不同的相关段落。最后,为了推断无序的训练段落中的跳跃依赖性,我们设计了潜在的跳跃订购,这是一种弱者的策略,在该策略中,受过训练的检索员本身选择了啤酒花的顺序。我们在检索中评估Baleen的两跳问答和多跳的要求验证,并确定最先进的绩效。
translated by 谷歌翻译
假新闻的检测往往需要复杂的推理技能,例如通过考虑单词级微妙的线索来逻辑地结合信息。在本文中,我们通过更好地反映人类思维的逻辑流程并实现微妙的线索建模,迈向假新闻检测的微粒推理。特别是,我们通过遵循人类信息处理模型提出了一种细粒度的推理框架,引入了一种基于互连的方法,以结合人类了解哪些证据更重要,并设计了一个先知的双通道内核图网络模拟证据之间的微妙差异。广泛的实验表明,我们的模型优于最先进的方法,并展示了我们的方法的解释性。
translated by 谷歌翻译
本文介绍了我们在Aaai 2022的多模态事实验证(Factifify)挑战的参与者系统。尽管最近基于文本的验证技术和大型预训练的多模式模型的跨视野和语言,但在申请方面取得了非常有限的工作自动化事实检查过程的多模式技术,特别考虑到社交媒体上的图像和视频的索赔和假新闻的普遍存在。在我们的工作中,挑战被视为多式联版征报任务并被诬陷为多级分类。提出并探索了两个基线方法,包括集合模型(组合两个Uni-Modal模型)和多模态注意力网络(在索赔和证据文件中建模图像和文本对之间的交互)。我们在这项工作中进行了调查和基准测试和基准测试的几个实验和基准测试。我们的最佳型号在排行榜中排名第一,在验证和测试集中获得0.77的加权平均f测量值。对DataSet的探索性分析也在辅助数据集上进行,并揭示了激励我们假设的突出模式和问题(例如,单词重叠,视觉着色相关性,来源偏见)。最后,我们突出了未来研究的任务和多模式数据集的挑战。
translated by 谷歌翻译
在视觉上丰富的文件(VRD)上的结构化文本理解是文档智能的重要组成部分。由于VRD中的内容和布局的复杂性,结构化文本理解是一项有挑战性的任务。大多数现有的研究将此问题与两个子任务结尾:实体标记和实体链接,这需要整体地了解令牌和段级别的文档的上下文。但是,很少的工作已经关注有效地从不同层次提取结构化数据的解决方案。本文提出了一个名为structext的统一框架,它对于处理两个子任务是灵活的,有效的。具体地,基于变压器,我们引入了一个段令牌对齐的编码器,以处理不同粒度水平的实体标记和实体链接任务。此外,我们设计了一种具有三个自我监督任务的新型预训练策略,以学习更丰富的代表性。 Structext使用现有屏蔽的视觉语言建模任务和新句子长度预测和配对框方向任务,以跨文本,图像和布局结合多模态信息。我们评估我们在分段级别和令牌级别的结构化文本理解的方法,并表明它优于最先进的同行,在Funsd,Srie和Ephoie数据集中具有显着优越的性能。
translated by 谷歌翻译
链接的语音实体旨在识别和消除语言中的命名实体。常规方法严重遭受了不受限制的语音样式和ASR系统产生的嘈杂笔录。在本文中,我们提出了一种名为“知识增强命名实体识别”(KENER)的新颖方法,该方法致力于通过在实体识别阶段无痛地纳入适当的知识来改善鲁棒性,从而改善实体联系的整体性能。肯纳(Kener)首先检索未提及的句子的候选实体,然后利用实体描述作为额外的信息来帮助识别提及。当输入短或嘈杂时,由密集检索模块检索的候选实体特别有用。此外,我们研究了各种数据采样策略和设计有效的损失功能,以提高识别和歧义阶段中检索实体的质量。最后,将与过滤模块的链接作为最终保障措施应用,从而可以过滤出错误认可的提及。我们的系统在NLPCC-2022共享任务2的轨道1中获得第一名,并在轨道1中获得第一名。
translated by 谷歌翻译
In this paper we introduce a new publicly available dataset for verification against textual sources, FEVER: Fact Extraction and VERification. It consists of 185,445 claims generated by altering sentences extracted from Wikipedia and subsequently verified without knowledge of the sentence they were derived from.The claims are classified as SUPPORTED, RE-FUTED or NOTENOUGHINFO by annotators achieving 0.6841 in Fleiss κ. For the first two classes, the annotators also recorded the sentence(s) forming the necessary evidence for their judgment. To characterize the challenge of the dataset presented, we develop a pipeline approach and compare it to suitably designed oracles. The best accuracy we achieve on labeling a claim accompanied by the correct evidence is 31.87%, while if we ignore the evidence we achieve 50.91%. Thus we believe that FEVER is a challenging testbed that will help stimulate progress on claim verification against textual sources.
translated by 谷歌翻译
Machine-Generated Text (MGT) detection, a task that discriminates MGT from Human-Written Text (HWT), plays a crucial role in preventing misuse of text generative models, which excel in mimicking human writing style recently. Latest proposed detectors usually take coarse text sequence as input and output some good results by fine-tune pretrained models with standard cross-entropy loss. However, these methods fail to consider the linguistic aspect of text (e.g., coherence) and sentence-level structures. Moreover, they lack the ability to handle the low-resource problem which could often happen in practice considering the enormous amount of textual data online. In this paper, we present a coherence-based contrastive learning model named CoCo to detect the possible MGT under low-resource scenario. Inspired by the distinctiveness and permanence properties of linguistic feature, we represent text as a coherence graph to capture its entity consistency, which is further encoded by the pretrained model and graph neural network. To tackle the challenges of data limitations, we employ a contrastive learning framework and propose an improved contrastive loss for making full use of hard negative samples in training stage. The experiment results on two public datasets prove our approach outperforms the state-of-art methods significantly.
translated by 谷歌翻译
排名模型是信息检索系统的主要组成部分。排名的几种方法是基于传统的机器学习算法,使用一组手工制作的功能。最近,研究人员在信息检索中利用了深度学习模型。这些模型的培训结束于结束,以提取来自RAW数据的特征来排序任务,因此它们克服了手工制作功能的局限性。已经提出了各种深度学习模型,每个模型都呈现了一组神经网络组件,以提取用于排名的特征。在本文中,我们在不同方面比较文献中提出的模型,以了解每个模型的主要贡献和限制。在我们对文献的讨论中,我们分析了有前途的神经元件,并提出了未来的研究方向。我们还显示文档检索和其他检索任务之间的类比,其中排名的项目是结构化文档,答案,图像和视频。
translated by 谷歌翻译
作为人类认知的重要组成部分,造成效果关系频繁出现在文本中,从文本策划原因关系有助于建立预测任务的因果网络。现有的因果关系提取技术包括基于知识的,统计机器学习(ML)和基于深度学习的方法。每种方法都具有其优点和缺点。例如,基于知识的方法是可以理解的,但需要广泛的手动域知识并具有较差的跨域适用性。由于自然语言处理(NLP)工具包,统计机器学习方法更加自动化。但是,功能工程是劳动密集型的,工具包可能导致错误传播。在过去的几年里,由于其强大的代表学习能力和计算资源的快速增加,深入学习技术吸引了NLP研究人员的大量关注。它们的局限包括高计算成本和缺乏足够的注释培训数据。在本文中,我们对因果关系提取进行了综合调查。我们最初介绍了因果关系提取中存在的主要形式:显式的内部管制因果关系,隐含因果关系和间情态因果关系。接下来,我们列出了代理关系提取的基准数据集和建模评估方法。然后,我们介绍了三种技术的结构化概述了与他们的代表系统。最后,我们突出了潜在的方向存在现有的开放挑战。
translated by 谷歌翻译
名人认可是品牌交流中最重要的策略之一。如今,越来越多的公司试图为自己建立生动的特征。因此,他们的品牌身份交流应符合人类和法规的某些特征。但是,以前的作品主要是通过假设停止的,而不是提出一种特定的品牌和名人之间匹配的方式。在本文中,我们建议基于自然语言处理(NLP)技术的品牌名人匹配模型(BCM)。鉴于品牌和名人,我们首先从互联网上获得了一些描述性文档,然后总结了这些文档,最后计算品牌和名人之间的匹配程度,以确定它们是否匹配。根据实验结果,我们提出的模型以0.362 F1得分和精度的6.3%优于最佳基线,这表明我们模型在现实世界中的有效性和应用值。更重要的是,据我们所知,拟议的BCM模型是使用NLP解决认可问题的第一项工作,因此它可以为以下工作提供一些新颖的研究思想和方法。
translated by 谷歌翻译
鉴于自然语言陈述,如何验证其对维基百科这样的大型文本知识来源的准确性吗?大多数现有的神经模型在不提供关于哪一部分错误的情况下出现问题的情况下会进行预测。在本文中,我们提出了Loren,一种可解释的事实验证的方法。我们分解了在短语级别的整个索赔的验证,其中短语的真实性用作解释,可以根据逻辑规则汇总到最终判决中。 Loren的关键洞察力是将索赔词如三值潜变量代表如下,由聚合逻辑规则规范化。最终索赔验证基于所有潜在的变量。因此,Loren享有可解释性的额外好处 - 很容易解释它如何通过索赔词来达到某些结果。关于公共事实验证基准的实验表明,Loren对以前的方法具有竞争力,同时享有忠实和准确的可解释性的优点。 Loren的资源可用于:https://github.com/jiangjiechen/loren。
translated by 谷歌翻译
The opaqueness of the multi-hop fact verification model imposes imperative requirements for explainability. One feasible way is to extract rationales, a subset of inputs, where the performance of prediction drops dramatically when being removed. Though being explainable, most rationale extraction methods for multi-hop fact verification explore the semantic information within each piece of evidence individually, while ignoring the topological information interaction among different pieces of evidence. Intuitively, a faithful rationale bears complementary information being able to extract other rationales through the multi-hop reasoning process. To tackle such disadvantages, we cast explainable multi-hop fact verification as subgraph extraction, which can be solved based on graph convolutional network (GCN) with salience-aware graph learning. In specific, GCN is utilized to incorporate the topological interaction information among multiple pieces of evidence for learning evidence representation. Meanwhile, to alleviate the influence of noisy evidence, the salience-aware graph perturbation is induced into the message passing of GCN. Moreover, the multi-task model with three diagnostic properties of rationale is elaborately designed to improve the quality of an explanation without any explicit annotations. Experimental results on the FEVEROUS benchmark show significant gains over previous state-of-the-art methods for both rationale extraction and fact verification.
translated by 谷歌翻译