大多数现有方法仅在所有实体都被识别之后才确定关系类型,因此关系类型和实体命令之间的交互没有完全建模。本文提出了一种新的范式,通过将相关实体视为关系的论证来处理关系提取。我们在这个范例中应用分层强化学习(HRL)框架来增强实体提及和关系类型之间的相互作用。整个提取过程分解为两级RL策略的层次结构,分别用于关系检测和实体提取,因此处理重叠关系更加可行和自然。我们的模型通过远程监督收集的公共数据集进行评估,结果表明它比现有方法获得更好的性能,并且更有助于提取重叠关系。
translated by 谷歌翻译
We show that relation extraction can be reduced to answering simple reading comprehension questions, by associating one or more natural-language questions with each relation slot. This reduction has several advantages: we can (1) learn relation-extraction models by extending recent neural reading-comprehension techniques, (2) build very large training sets for those models by combining relation-specific crowd-sourced questions with distant supervision , and even (3) do zero-shot learning by extracting new relation types that are only specified at test-time, for which we have no labeled training examples. Experiments on a Wikipedia slot-filling task demonstrate that the approach can generalize to new questions for known relation types with high accuracy, and that zero-shot generalization to unseen relation types is possible, at lower accuracy levels, setting the bar for future work on this task.
translated by 谷歌翻译
用于联合实体识别和关系提取的最先进模型完全依赖于外部自然语言处理(NLP)工具,例如POS(词性)标记器和依赖性解析器。因此,这种联合模型的性能取决于从这些NLP工具获得的特征的质量。但是,对于各种语言和上下文,这些功能并不总是准确的。在本文中,我们提出了一种联合神经模型,它同时进行表现识别和关系提取,无需任何手动提取的特征或使用任何外部工具。具体地,我们使用CRF(条件随机场)层和关系提取任务将实体识别任务建模为多头选择问题(即,潜在地识别每个实体的多个关系)。我们提供了一个广泛的实验设置,以使用来自各种环境(即新闻,生物医学,房地产)和语言(即英语,荷兰语)的数据集来证明我们方法的有效性。我们的模型优于以前使用自动提取特征的神经模型,同时它在基于特征的神经模型的合理边缘内执行,甚至胜过它们。
translated by 谷歌翻译
We present a novel attention-based recurrent neural network for joint extraction of entity mentions and relations. We show that attention along with long short term memory (LSTM) network can extract semantic relations between entity mentions without having access to dependency trees. Experiments on Automatic Content Extraction (ACE) corpora show that our model significantly outperforms feature-based joint model by Li and Ji (2014). We also compare our model with an end-to-end tree-based LSTM model (SPTree) by Miwa and Bansal (2016) and show that our model performs within 1% on entity mentions and 2% on relations. Our fine-grained analysis also shows that our model performs significantly better on AGENT-ARTIFACT relations, while SPTree performs better on PHYSICAL and PART-WHOLE relations.
translated by 谷歌翻译
在这项工作中,我们介绍了开放式关系参数提取(ORAE)的任务:给定语料库,查询实体Q和知识库关系(例如,“Qauthored notable work with title X”),模型必须提取来自语料库的非标准实体类型的参数(不能由标准名称标记符提取的实体,例如X:书籍或艺术作品的标题)。获得并发布基于WikiData关系的受监督数据集以解决该任务。我们为这项任务开发和比较了广泛的神经模型,在通过神经问答系统获得的强基线上进行了大幅改进。系统地比较了不同句子编码体系结构和提取方法的影响。基于gatedrecurrent单元的编码器与条件随机字段标记器相结合,可以得到最好的结果。
translated by 谷歌翻译
We investigate applying repurposed generic QA data and models to a recently proposed relation extraction task. We find that training on SQuAD produces better zero-shot performance and more robust generalisation compared to the task specific training set. We also show that standard QA architectures (e.g. FastQA or BiDAF) can be applied to the slot filling queries without the need for model modification.
translated by 谷歌翻译
This paper proposes a framework for automatically engineering features for two important tasks of question answering: answer sentence selection and answer extraction. We represent question and answer sentence pairs with linguistic structures enriched by semantic information , where the latter is produced by automatic classifiers, e.g., question classifier and Named Entity Recognizer. Tree kernels applied to such structures enable a simple way to generate highly discriminative structural features that combine syntactic and semantic information encoded in the input trees. We conduct experiments on a public benchmark from TREC to compare with previous systems for answer sentence selection and answer extraction. The results show that our models greatly improve on the state of the art, e.g., up to 22% on F1 (relative improvement) for answer extraction , while using no additional resources and no manual feature engineering.
translated by 谷歌翻译
Joint extraction of entities and relations is an important task in information extraction. To tackle this problem, we firstly propose a novel tagging scheme that can convert the joint extraction task to a tagging problem. Then, based on our tagging scheme, we study different end-to-end models to extract entities and their relations directly, without identifying entities and relations separately. We conduct experiments on a public dataset produced by distant supervision method and the experimental results show that the tagging based methods are better than most of the existing pipelined and joint learning methods. What's more, the end-to-end model proposed in this paper, achieves the best results on the public dataset.
translated by 谷歌翻译
深度学习可以单独提高许多自然语言处理(NLP)任务的性能。但是,一般的NLP模型不能出现在一个侧重于单个度量,数据集和任务的特殊性的范例内。我们介绍了自然语言十项全能(decaNLP),这是一个跨越十个任务的挑战:问答,机器翻译,摘要,自然语言推理,情感分析,语义角色标记,零镜头关系提取,目标导向对话,语义分析和常识代名词决议。我们通过acontext将所有任务作为问题回答。此外,我们提出了一个新的多任务问题应答网络(MQAN),在多任务设置中联合学习decaNLP中的所有任务,而不需要任何特定于任务的模块或参数。 MQAN显示了机器翻译和命名实体识别的转移学习,情感分析和自然语言推理的域适应以及文本分类的零镜头能力方面的改进。我们证明了MQAN的多指针生成器解码器是这一成功的关键,并且通过反课程培训策略进一步提高了性能。虽然设计用于decaNLP,但MQAN还在单任务设置中的WikiSQL语义分析任务上实现了最先进的结果。我们还发布了采购和处理数据,培训和评估模型以及为decaNLP复制实验的代码。
translated by 谷歌翻译
Information Extraction (IE) refers to automatically extracting struc-tured relation tuples from unstructured texts. Common IE solutions, including Relation Extraction (RE) and open IE systems, can hardly handle cross-sentence tuples, and are severely restricted by limited relation types as well as informal relation specifications (e.g., free-text based relation tuples). In order to overcome these weaknesses, we propose a novel IE framework named QA4IE, which leverages the flexible question answering (QA) approaches to produce high quality relation triples across sentences. Based on the framework, we develop a large IE benchmark with high quality human evaluation. This benchmark contains 293K documents, 2M golden relation triples, and 636 relation types. We compare our system with some IE baselines on our benchmark and the results show that our system achieves great improvements.
translated by 谷歌翻译
我们考虑开放域查询答案(QA),其中从语料库,知识库(KB)或这两者的组合中得出答案。我们专注于一个设置,在这个环境中,语料库补充了大量但不完整的KB,以及需要非平凡(例如,“多跳”)推理的问题。我们描述了PullNet,这是一个集成框架,用于(1)学习检索什么(从KB和/或语料库中)和(2)使用这种异构信息进行推理以找到最佳答案。 PullNet使用{迭代}过程来构建一个特定于问题的子图,其中包含与问题相关的信息。在每次迭代中,图形卷积网络(图形CNN)用于识别应该使用语料库和/或KB上的检索(或“拉”)操作来扩展的子图节点。在完成subgraphis之后,使用类似的图CNN从子图中提取答案。这个检索和推理过程允许我们使用大型KB和语料库来回答多跳问题。 PullNet受到弱监督,需要问题 - 答案对而不是黄金推理路径。实验性地提高了先前技术水平,并且在语料库使用不完整KB的环境中,这些改进通常是戏剧性的。 PullNet在仅KB设置或纯文本设置中也优于以前的系统。
translated by 谷歌翻译
Existing knowledge-based question answering systems often rely on small annotated training data. While shallow methods like relation extraction are robust to data scarcity, they are less expressive than the deep meaning representation methods like semantic parsing, thereby failing at answering questions involving multiple constraints. Here we alleviate this problem by empowering a relation extraction method with additional evidence from Wikipedia. We first present a neural network based relation extractor to retrieve the candidate answers from Freebase, and then infer over Wikipedia to validate these answers. Experiments on the WebQuestions question answering dataset show that our method achieves an F 1 of 53.3%, a substantial improvement over the state-of-the-art.
translated by 谷歌翻译
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for standard maximum likelihood training, we fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality. Most notably, one of these rewards is the performance of a question-answering system. Our model is trained and evaluated on the recent question-answering dataset SQuAD.
translated by 谷歌翻译
问答(QA)作为一个研究领域,主要关注知识库(KB)或自由文本作为知识来源。这两个来源在历史上形成了通过资源提出的各种问题,以及为解决这些问题而开发的方法。在这项工作中,我们看到QA的实际用例,而不是用户指导的知识,它将结构化QA的元素与知识库,非结构化QA与叙述相结合,将多关系QA的任务引入个人叙述。作为实现这一目标的第一步,我们做出了三个关键贡献:(i)我们生成并发布TextWorldsQA,一组五个不同的数据集,whereeach数据集包含动态叙述,描述模拟世界中的实体和关系,与可变组成问题配对知识,(ii)我们在这项任务中对几个最先进的QA模型及其变体进行了全面的评估和分析,以及(iii)发布了一个轻量级的基于Python的框架,我们称之为TextWorlds,可以轻松生成任意的额外世界和叙事,目标是允许社区创建和分享越来越多的不同世界作为此任务的测试平台。
translated by 谷歌翻译
深度学习方法采用多个处理层来学习数据的层次表示,并在manydomains中产生了最先进的结果。最近,各种模型设计和方法在自然语言处理(NLP)的背景下蓬勃发展。在本文中,我们回顾了已经用于大量NLP任务的重要深度学习相关模型和方法,并提供了他们演变的演练。我们对各种模型进行了比较,比较和对比,并对NLP深度学习的过去,现在和未来进行了详细的理解。
translated by 谷歌翻译
随着数字时代的兴起,新闻,文章,社交媒体等形式的信息爆炸式增长。这些数据大部分在于非结构化形式,人工管理和有效利用它是繁琐,乏味和劳动密集型的。信息爆炸以及对更复杂和有效的信息处理工具的需求促成了信息提取(IE)和信息检索(IR)技术。信息提取系统将自然语言文本作为输入并产生由特定标准指定的结构化信息,这与特定的相关。应用。 IE的各种子任务,如命名实体识别,共指解析,命名实体链接,关系提取,知识库推理,形成各种高端自然语言处理(NLP)任务的构建块,如机器翻译,问答系统,自然语言理解,Text Summarization和DigitalAssistants,如Siri,Cortana和Google Now。本文介绍了InformationExtraction技术及其各种子任务,重点介绍了各种IE子任务中的最新研究,当前的挑战和未来的研究方向。
translated by 谷歌翻译
谁做了什么对谁来说是自然语言理解的主要焦点,这是语义角色标记(SRL)的目标。虽然SRL对于文本理解任务来说是自然必不可少的,但在以前的工作中却令人惊讶地被忽略了。因此,本文首次尝试让SRL通过指定语言参数及其相应的语义角色来增强文本理解和推理。在深度学习模型方面,我们的嵌入由语义角色标签增强,以实现更细粒度的语义。我们展示了显着标签可以方便地添加到现有模型中,并显着改善具有挑战性的文本理解功能的深度学习模型。对基准机器阅读理解和推论数据集的广泛实验验证了所提出的语义学习有助于我们的系统达到新的最新技术水平。
translated by 谷歌翻译
我们提出了一个新的CogQA框架,用于多跳问题回答inweb-scale文档。受认知科学中的双重过程理论的启发,该框架通过协调隐式提取模块(系统1)和显式推理模块(系统2)逐步在迭代过程中构建\ textit {认知图}。在给出准确答案的同时,我们的框架进一步提供了可解释的推理路径。具体而言,基于BERT和图形神经网络的实现有效处理了HotpotQAfullwiki数据集中的多跳推理问题的数百万个文档,在排行榜上获得了34.9的联合$ F_1 $得分,而最佳竞争对手的得分为23.6。
translated by 谷歌翻译
Our goal is to extract answers from pre-retrieved sentences for Question Answering (QA). We construct a linear-chain Conditional Random Field based on pairs of questions and their possible answer sentences, learning the association between questions and answer types. This casts answer extraction as an answer sequence tagging problem for the first time, where knowledge of shared structure between question and source sentence is incorporated through features based on Tree Edit Distance (TED). Our model is free of manually created question and answer templates, fast to run (processing 200 QA pairs per second excluding parsing time), and yields an F1 of 63.3% on a new public dataset based on prior TREC QA evaluations. The developed system is open-source, and includes an implementation of the TED model that is state of the art in the task of ranking QA pairs.
translated by 谷歌翻译
We present an incremental joint framework to simultaneously extract entity mentions and relations using structured per-ceptron with efficient beam-search. A segment-based decoder based on the idea of semi-Markov chain is adopted to the new framework as opposed to traditional token-based tagging. In addition, by virtue of the inexact search, we developed a number of new and effective global features as soft constraints to capture the inter-dependency among entity mentions and relations. Experiments on Automatic Content Extraction (ACE) 1 corpora demonstrate that our joint model significantly outperforms a strong pipelined baseline, which attains better performance than the best-reported end-to-end system.
translated by 谷歌翻译