大量培训数据是最先进的NLP模型高性能的主要原因之一。但是,在培训数据中,什么导致模型做出一定的预测?我们试图通过提供一种通过因果框架来描述培训数据如何影响预测的语言来回答这个问题。重要的是,我们的框架绕过了重新培训昂贵模型的需求,并使我们能够仅基于观察数据来估计因果效应。解决从验证的语言模型(PLM)中提取事实知识的问题,我们重点介绍了简单的数据统计数据,例如共发生计数,并表明这些统计数据确实会影响PLM的预测,这表明此类模型依赖于浅启发式方法。我们的因果框架和结果表明,研究数据集的重要性以及因果关系对理解NLP模型的好处。
translated by 谷歌翻译
基于变压器的语言模型最近在许多自然语言任务中取得了显着的结果。但是,通常通过利用大量培训数据来实现排行榜的性能,并且很少通过将明确的语言知识编码为神经模型。这使许多人质疑语言学对现代自然语言处理的相关性。在本文中,我介绍了几个案例研究,以说明理论语言学和神经语言模型仍然相互关联。首先,语言模型通过提供一个客观的工具来测量语义距离,这对语言学家很有用,语义距离很难使用传统方法。另一方面,语言理论通过提供框架和数据源来探究我们的语言模型,以了解语言理解的特定方面,从而有助于语言建模研究。本论文贡献了三项研究,探讨了语言模型中语法 - 听觉界面的不同方面。在论文的第一部分中,我将语言模型应用于单词类灵活性的问题。我将Mbert作为语义距离测量的来源,我提供了有利于将单词类灵活性分析为方向过程的证据。在论文的第二部分中,我提出了一种方法来测量语言模型中间层的惊奇方法。我的实验表明,包含形态句法异常的句子触发了语言模型早期的惊喜,而不是语义和常识异常。最后,在论文的第三部分中,我适应了一些心理语言学研究,以表明语言模型包含了论证结构结构的知识。总而言之,我的论文在自然语言处理,语言理论和心理语言学之间建立了新的联系,以为语言模型的解释提供新的观点。
translated by 谷歌翻译
petroni等。 (2019)证明,可以通过将它们表达为冻结式提示并将模型的预测准确性解释为下限,作为其编码的事实信息量的较低限制,从预先接收的语言模型中检索世界事实。随后的工作已经尝试通过搜索更好的提示来缩回估计,使用不相交的事实作为培训数据。在这项工作中,我们制作两个互补贡献,以更好地了解这些事实探测技术。首先,我们提出了OptiPrompt,一种新颖的和有效的方法,直接在连续嵌入空间中优化。我们发现这种简单的方法能够预测喇嘛基准中的额外6.4%的事实。其次,我们提出了一个更重要的问题:我们真的可以将这些探测结果解释为下限吗?这些提示搜索方法是否有可能从培训数据中学习?我们发现,有些令人惊讶的是,这些方法使用的培训数据包含了潜在的事实分布的某些规则,以及所有现有的提示方法,包括我们的方法,可以利用它们以获得更好的事实预测。我们开展一系列控制实验来解除“学习”从“学习召回”,提供了更详细的图片,不同的提示可以揭示关于预先接受的语言模型。
translated by 谷歌翻译
The remarkable success of pretrained language models has motivated the study of what kinds of knowledge these models learn during pretraining. Reformulating tasks as fillin-the-blanks problems (e.g., cloze tests) is a natural approach for gauging such knowledge, however, its usage is limited by the manual effort and guesswork required to write suitable prompts. To address this, we develop AUTOPROMPT, an automated method to create prompts for a diverse set of tasks, based on a gradient-guided search. Using AUTO-PROMPT, we show that masked language models (MLMs) have an inherent capability to perform sentiment analysis and natural language inference without additional parameters or finetuning, sometimes achieving performance on par with recent state-of-the-art supervised models. We also show that our prompts elicit more accurate factual knowledge from MLMs than the manually created prompts on the LAMA benchmark, and that MLMs can be used as relation extractors more effectively than supervised relation extraction models. These results demonstrate that automatically generated prompts are a viable parameter-free alternative to existing probing methods, and as pretrained LMs become more sophisticated and capable, potentially a replacement for finetuning.
translated by 谷歌翻译
我们研究了现代神经语言模型容易受到结构启动的程度,这种现象使句子的结构在后续句子中更有可能使相同的结构更有可能。我们探索如何使用启动来研究这些模型学习抽象结构信息的潜力,这是需要自然语言理解技能的任务良好表现的先决条件。我们引入了一种新型的度量标准和释放Prime-LM,这是一个大型语料库,我们可以控制与启动强度相互作用的各种语言因素。我们发现,变压器模型确实显示了结构启动的证据,但他们所学到的概括在某种程度上是由语义信息调节的。我们的实验还表明,模型获得的表示不仅可以编码抽象的顺序结构,而且还涉及一定级别的层次句法信息。更普遍的是,我们的研究表明,启动范式是一种有用的,可用于洞悉语言模型能力的有用的,并为未来的基于底漆的调查打开了探测模型内部状态的未来大门。
translated by 谷歌翻译
Transformer-based models have pushed state of the art in many areas of NLP, but our understanding of what is behind their success is still limited. This paper is the first survey of over 150 studies of the popular BERT model. We review the current state of knowledge about how BERT works, what kind of information it learns and how it is represented, common modifications to its training objectives and architecture, the overparameterization issue and approaches to compression. We then outline directions for future research.
translated by 谷歌翻译
Recent progress in pretraining language models on large textual corpora led to a surge of improvements for downstream NLP tasks. Whilst learning linguistic knowledge, these models may also be storing relational knowledge present in the training data, and may be able to answer queries structured as "fillin-the-blank" cloze statements. Language models have many advantages over structured knowledge bases: they require no schema engineering, allow practitioners to query about an open class of relations, are easy to extend to more data, and require no human supervision to train. We present an in-depth analysis of the relational knowledge already present (without fine-tuning) in a wide range of state-of-theart pretrained language models. We find that (i) without fine-tuning, BERT contains relational knowledge competitive with traditional NLP methods that have some access to oracle knowledge, (ii) BERT also does remarkably well on open-domain question answering against a supervised baseline, and (iii) certain types of factual knowledge are learned much more readily than others by standard language model pretraining approaches. The surprisingly strong ability of these models to recall factual knowledge without any fine-tuning demonstrates their potential as unsupervised open-domain QA systems. The code to reproduce our analysis is available at https: //github.com/facebookresearch/LAMA.
translated by 谷歌翻译
众所周知,端到端的神经NLP体系结构很难理解,这引起了近年来为解释性建模的许多努力。模型解释的基本原则是忠诚,即,解释应准确地代表模型预测背后的推理过程。这项调查首先讨论了忠诚的定义和评估及其对解释性的意义。然后,我们通过将方法分为五类来介绍忠实解释的最新进展:相似性方法,模型内部结构的分析,基于反向传播的方法,反事实干预和自我解释模型。每个类别将通过其代表性研究,优势和缺点来说明。最后,我们从它们的共同美德和局限性方面讨论了上述所有方法,并反思未来的工作方向忠实的解释性。对于有兴趣研究可解释性的研究人员,这项调查将为该领域提供可访问且全面的概述,为进一步探索提供基础。对于希望更好地了解自己的模型的用户,该调查将是一项介绍性手册,帮助选择最合适的解释方法。
translated by 谷歌翻译
Recent work has presented intriguing results examining the knowledge contained in language models (LM) by having the LM fill in the blanks of prompts such as "Obama is a by profession". These prompts are usually manually created, and quite possibly suboptimal; another prompt such as "Obama worked as a " may result in more accurately predicting the correct profession. Because of this, given an inappropriate prompt, we might fail to retrieve facts that the LM does know, and thus any given prompt only provides a lower bound estimate of the knowledge contained in an LM. In this paper, we attempt to more accurately estimate the knowledge contained in LMs by automatically discovering better prompts to use in this querying process. Specifically, we propose mining-based and paraphrasing-based methods to automatically generate high-quality and diverse prompts, as well as ensemble methods to combine answers from different prompts. Extensive experiments on the LAMA benchmark for extracting relational knowledge from LMs demonstrate that our methods can improve accuracy from 31.1% to 39.6%, providing a tighter lower bound on what LMs know. We have released the code and the resulting LM Prompt And Query Archive (LPAQA) at https://github. com/jzbjyb/LPAQA.1 Some models we use in this paper, e.g. BERT (Devlin et al., 2019), are bi-directional, and do not directly define probability distribution over text, which is the underlying definition of an LM. Nonetheless, we call them LMs for simplicity.
translated by 谷歌翻译
The long-distance agreement, evidence for syntactic structure, is increasingly used to assess the syntactic generalization of Neural Language Models. Much work has shown that transformers are capable of high accuracy in varied agreement tasks, but the mechanisms by which the models accomplish this behavior are still not well understood. To better understand transformers' internal working, this work contrasts how they handle two superficially similar but theoretically distinct agreement phenomena: subject-verb and object-past participle agreement in French. Using probing and counterfactual analysis methods, our experiments show that i) the agreement task suffers from several confounders which partially question the conclusions drawn so far and ii) transformers handle subject-verb and object-past participle agreements in a way that is consistent with their modeling in theoretical linguistics.
translated by 谷歌翻译
语言可以用作再现和执行有害刻板印象和偏差的手段,并被分析在许多研究中。在本文中,我们对自然语言处理中的性别偏见进行了304篇论文。我们分析了社会科学中性别及其类别的定义,并将其连接到NLP研究中性别偏见的正式定义。我们调查了在对性别偏见的研究中应用的Lexica和数据集,然后比较和对比方法来检测和减轻性别偏见。我们发现对性别偏见的研究遭受了四个核心限制。 1)大多数研究将性别视为忽视其流动性和连续性的二元变量。 2)大部分工作都在单机设置中进行英语或其他高资源语言进行。 3)尽管在NLP方法中对性别偏见进行了无数的论文,但我们发现大多数新开发的算法都没有测试他们的偏见模型,并无视他们的工作的伦理考虑。 4)最后,在这一研究线上发展的方法基本缺陷涵盖性别偏差的非常有限的定义,缺乏评估基线和管道。我们建议建议克服这些限制作为未来研究的指导。
translated by 谷歌翻译
在NLP社区中有一个正在进行的辩论,无论现代语言模型是否包含语言知识,通过所谓的探针恢复。在本文中,我们研究了语言知识是否是现代语言模型良好表现的必要条件,我们称之为\ Texit {重新发现假设}。首先,我们展示了语言模型,这是显着压缩的,但在预先磨普目标上表现良好,以便在语言结构探讨时保持良好的分数。这一结果支持重新发现的假设,并导致我们的论文的第二款贡献:一个信息 - 理论框架,与语言建模目标相关。该框架还提供了测量语言信息对字词预测任务的影响的度量标准。我们通过英语综合和真正的NLP任务加固我们的分析结果。
translated by 谷歌翻译
自然语言处理的机器学习快速进步有可能改变有关人类学习语言的辩论。但是,当前人工学习者和人类的学习环境和偏见以削弱从学习模拟获得的证据的影响的方式分歧。例如,当今最有效的神经语言模型接受了典型儿童可用的语言数据量的大约一千倍。为了增加计算模型的可学习性结果的相关性,我们需要培训模型学习者,而没有比人类具有显着优势的学习者。如果合适的模型成功地获得了一些目标语言知识,则可以提供一个概念证明,即在假设的人类学习方案中可以学习目标。合理的模型学习者将使我们能够进行实验操作,以对学习环境中的变量进行因果推断,并严格测试史密斯风格的贫困声明,主张根据人类对人类的先天语言知识,基于有关可学习性的猜测。由于实用和道德的考虑因素,人类受试者将永远无法实现可比的实验,从而使模型学习者成为必不可少的资源。到目前为止,试图剥夺当前模型的不公平优势,为关键语法行为(例如可接受性判断)获得亚人类结果。但是,在我们可以合理地得出结论,语言学习需要比当前模型拥有更多的特定领域知识,我们必须首先以多模式刺激和多代理互动的形式探索非语言意见,以使学习者更有效地学习学习者来自有限的语言输入。
translated by 谷歌翻译
因果关系是理解世界的科学努力的基本组成部分。不幸的是,在心理学和社会科学中,因果关系仍然是禁忌。由于越来越多的建议采用因果方法进行研究的重要性,我们重新制定了心理学研究方法的典型方法,以使不可避免的因果理论与其余的研究渠道协调。我们提出了一个新的过程,该过程始于从因果发现和机器学习的融合中纳入技术的发展,验证和透明的理论形式规范。然后,我们提出将完全指定的理论模型的复杂性降低到与给定目标假设相关的基本子模型中的方法。从这里,我们确定利息量是否可以从数据中估算出来,如果是的,则建议使用半参数机器学习方法来估计因果关系。总体目标是介绍新的研究管道,该管道可以(a)促进与测试因果理论的愿望兼容的科学询问(b)鼓励我们的理论透明代表作为明确的数学对象,(c)将我们的统计模型绑定到我们的统计模型中该理论的特定属性,因此减少了理论到模型间隙通常引起的规范不足问题,以及(d)产生因果关系和可重复性的结果和估计。通过具有现实世界数据的教学示例来证明该过程,我们以摘要和讨论来结论。
translated by 谷歌翻译
现在,通过复杂的神经网络模型(例如蒙版的神经语言模型(MNLM))学习了许多上下文化的单词表示形式,这些模型由巨大的神经网络结构组成,并经过训练以恢复蒙面文本。这样的表示表明在某些阅读理解(RC)任务中表现出超人的表现,这些任务在给出问题的上下文中提取了适当的答案。但是,由于许多模型参数,确定在MNLM中训练的详细知识是具有挑战性的。本文提供了有关MNLMS中包含的常识性知识的新见解和经验分析。首先,我们使用诊断测试来评估常识性知识是否在MNLMS中进行了适当的培训。我们观察到,在MNLMS中没有适当训练很多常识性知识,并且MNLMS并不经常准确地理解关系的语义含义。此外,我们发现基于MNLM的RC模型仍然容易受到需要常识知识的语义变化的影响。最后,我们发现了未经训练的知识的基本原因。我们进一步建议,利用外常识性知识存储库可以是一个有效的解决方案。我们说明了通过在受控实验中以外常识性知识存储库来丰富文本的经文,以克服基于MNLM的RC模型的局限性的可能性。
translated by 谷歌翻译
基于AI和机器学习的决策系统已在各种现实世界中都使用,包括医疗保健,执法,教育和金融。不再是牵强的,即设想一个未来,自治系统将推动整个业务决策,并且更广泛地支持大规模决策基础设施以解决社会最具挑战性的问题。当人类做出决定时,不公平和歧视的问题普遍存在,并且当使用几乎没有透明度,问责制和公平性的机器做出决定时(或可能会放大)。在本文中,我们介绍了\ textit {Causal公平分析}的框架,目的是填补此差距,即理解,建模,并可能解决决策设置中的公平性问题。我们方法的主要见解是将观察到数据中存在的差异的量化与基本且通常是未观察到的因果机制收集的因果机制的收集,这些机制首先会产生差异,挑战我们称之为因果公平的基本问题分析(FPCFA)。为了解决FPCFA,我们研究了分解差异和公平性的经验度量的问题,将这种变化归因于结构机制和人群的不同单位。我们的努力最终达到了公平地图,这是组织和解释文献中不同标准之间关系的首次系统尝试。最后,我们研究了进行因果公平分析并提出一本公平食谱的最低因果假设,该假设使数据科学家能够评估不同影响和不同治疗的存在。
translated by 谷歌翻译
科学研究的基本目标是了解因果关系。然而,尽管因果关系在生活和社会科学中的重要作用,但在自然语言处理(NLP)中并不具有相同的重要性,而自然语言处理(NLP)传统上更加重视预测任务。这种区别开始逐渐消失,随着因果推理和语言处理的融合,跨学科研究的新兴领域。尽管如此,关于NLP因果关系的研究仍然散布在没有统一的定义,基准数据集的情况下,并清楚地表达了将因果推论应用于文本领域的挑战和机遇,并具有其独特的属性。在这项调查中,我们巩固了整个学术领域的研究,并将其置于更广泛的NLP景观中。我们介绍了用文本估算因果效应的统计挑战,其中包含文本用作结果,治疗或解决混杂问题的设置。此外,我们探讨了因果推理的潜在用途,以提高NLP模型的鲁棒性,公平性和解释性。因此,我们提供了NLP社区因果推断的统一概述。
translated by 谷歌翻译
This review presents empirical researchers with recent advances in causal inference, and stresses the paradigmatic shifts that must be undertaken in moving from traditional statistical analysis to causal analysis of multivariate data. Special emphasis is placed on the assumptions that underly all causal inferences, the languages used in formulating those assumptions, the conditional nature of all causal and counterfactual claims, and the methods that have been developed for the assessment of such claims. These advances are illustrated using a general theory of causation based on the Structural Causal Model (SCM) described in Pearl (2000a), which subsumes and unifies other approaches to causation, and provides a coherent mathematical foundation for the analysis of causes and counterfactuals. In particular, the paper surveys the development of mathematical tools for inferring (from a combination of data and assumptions) answers to three types of causal queries: (1) queries about the effects of potential interventions, (also called "causal effects" or "policy evaluation") (2) queries about probabilities of counterfactuals, (including assessment of "regret," "attribution" or "causes of effects") and (3) queries about direct and indirect effects (also known as "mediation"). Finally, the paper defines the formal and conceptual relationships between the structural and potential-outcome frameworks and presents tools for a symbiotic analysis that uses the strong features of both.
translated by 谷歌翻译
语言模型(LMS)已被证明在各种下游应用程序中很有用,例如摘要,翻译,问答和文本分类。由于它们可以存储的大量信息,LMS正在成为人工智能中越来越重要的工具。在这项工作中,我们提出了道具(提示为探测),该道具利用GPT-3(最初由OpenAI在2020年提出的大型语言模型)来执行知识基础构建任务(KBC)。 Prop实施了一种多步骤方法,该方法结合了各种提示技术来实现这一目标。我们的结果表明,手动提示策划是必不可少的,必须鼓励LM给出可变长度的答案集,特别是包括空的答案集,True/False问题是提高LM生成的建议精度的有用设备。 LM的大小是至关重要的因素,并且实体字典别名提高了LM评分。我们的评估研究表明,这些提出的技术可以大大提高最终预测的质量:Prop赢得了LM-KBC竞争的轨道2,表现优于基线36.4个百分点。我们的实施可在https://github.com/hemile/iswc-challenge上获得。
translated by 谷歌翻译
Despite being responsible for state-of-the-art results in several computer vision and natural language processing tasks, neural networks have faced harsh criticism due to some of their current shortcomings. One of them is that neural networks are correlation machines prone to model biases within the data instead of focusing on actual useful causal relationships. This problem is particularly serious in application domains affected by aspects such as race, gender, and age. To prevent models from incurring on unfair decision-making, the AI community has concentrated efforts in correcting algorithmic biases, giving rise to the research area now widely known as fairness in AI. In this survey paper, we provide an in-depth overview of the main debiasing methods for fairness-aware neural networks in the context of vision and language research. We propose a novel taxonomy to better organize the literature on debiasing methods for fairness, and we discuss the current challenges, trends, and important future work directions for the interested researcher and practitioner.
translated by 谷歌翻译