预先训练的语言模型在多大程度上了解有关分发性现象的语义知识?在本文中,我们介绍了Distnli,这是一种新的自然语言推理诊断数据集,该数据集针对分布式引起的语义差异,并采用因果中介分析框架来量化模型行为并探索该语义相关任务中的基本机制。我们发现,模型的理解程度与模型大小和词汇大小有关。我们还提供有关模型如何编码这种高级语义知识的见解。
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
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
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
对于自然语言处理系统,两种证据支持在大型未解除的基层上的神经语言模型中使用文本表示:在应用程序启发基准上的表现(Peters等,2018年,除其他外)以及出现的出现这些陈述中的句法抽象(Tenney等,2019年,尤其)。另一方面,缺乏接地的监督呼吁质疑这些表现如何捕获意义(Bender和Koller,2020)。我们对最近的语言模型应用小说探针 - 特别关注由语义依赖性运作的谓词参数结构(Ivanova等,2012) - 并发现,与语法不同,语义不是通过今天的预磨款模型带到表面上。然后,我们使用卷积图编码器将语义解析明确地将语义解析结合到特定于任务的FineTuning中,为胶水基准测试中的自然语言理解(NLU)任务产生益处。这种方法展示了通用(而不是任务特定的)语言监督的潜力,以上和超越传统的预威胁和芬特。有几个诊断有助于本地化我们方法的好处。
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
尽管在理解深度NLP模型中学到的表示形式以及他们所捕获的知识方面已经做了很多工作,但对单个神经元的关注很少。我们提出了一种称为语言相关性分析的技术,可在任何外部特性中提取模型中的显着神经元 - 目的是了解如何保留这种知识在神经元中。我们进行了细粒度的分析以回答以下问题:(i)我们可以识别网络中捕获特定语言特性的神经元子集吗? (ii)整个网络中的局部或分布式神经元如何? iii)信息保留了多么冗余? iv)针对下游NLP任务的微调预训练模型如何影响学习的语言知识? iv)架构在学习不同的语言特性方面有何不同?我们的数据驱动的定量分析阐明了有趣的发现:(i)我们发现了可以预测不同语言任务的神经元的小亚集,ii)捕获基本的词汇信息(例如后缀),而这些神经元位于较低的大多数层中,iii,iii),而这些神经元,而那些神经元,而那些神经元则可以预测。学习复杂的概念(例如句法角色)主要是在中间和更高层中,iii),在转移学习过程中,显着的语言神经元从较高到较低的层移至较低的层,因为网络保留了较高的层以特定于任务信息,iv)我们发现很有趣在培训预训练模型之间的差异,关于如何保留语言信息,V)我们发现概念在多语言变压器模型中跨不同语言表现出相似的神经元分布。我们的代码作为Neurox工具包的一部分公开可用。
translated by 谷歌翻译
People constantly use language to learn about the world. Computational linguists have capitalized on this fact to build large language models (LLMs) that acquire co-occurrence-based knowledge from language corpora. LLMs achieve impressive performance on many tasks, but the robustness of their world knowledge has been questioned. Here, we ask: do LLMs acquire generalized knowledge about real-world events? Using curated sets of minimal sentence pairs (n=1215), we tested whether LLMs are more likely to generate plausible event descriptions compared to their implausible counterparts. We found that LLMs systematically distinguish possible and impossible events (The teacher bought the laptop vs. The laptop bought the teacher) but fall short of human performance when distinguishing likely and unlikely events (The nanny tutored the boy vs. The boy tutored the nanny). In follow-up analyses, we show that (i) LLM scores are driven by both plausibility and surface-level sentence features, (ii) LLMs generalize well across syntactic sentence variants (active vs passive) but less well across semantic sentence variants (synonymous sentences), (iii) some, but not all LLM deviations from ground-truth labels align with crowdsourced human judgments, and (iv) explicit event plausibility information emerges in middle LLM layers and remains high thereafter. Overall, our analyses reveal a gap in LLMs' event knowledge, highlighting their limitations as generalized knowledge bases. We conclude by speculating that the differential performance on impossible vs. unlikely events is not a temporary setback but an inherent property of LLMs, reflecting a fundamental difference between linguistic knowledge and world knowledge in intelligent systems.
translated by 谷歌翻译
数据饥饿的深度神经网络已经将自己作为许多NLP任务的标准建立为包括传统序列标记的标准。尽管他们在高资源语言上表现最先进的表现,但它们仍然落后于低资源场景的统计计数器。一个方法来反击攻击此问题是文本增强,即,从现有数据生成新的合成训练数据点。虽然NLP最近目睹了一种文本增强技术的负载,但该领域仍然缺乏对多种语言和序列标记任务的系统性能分析。为了填补这一差距,我们调查了三类文本增强方法,其在语法(例如,裁剪子句子),令牌(例如,随机字插入)和字符(例如,字符交换)级别上执行更改。我们系统地将它们与语音标记,依赖解析和语义角色标记的分组进行了比较,用于使用各种模型的各种语言系列,包括依赖于诸如MBERT的普赖金的多语言语境化语言模型的架构。增强最显着改善了解析,然后是语音标记和语义角色标记的依赖性解析。我们发现实验技术通常在形态上丰富的语言,而不是越南语等分析语言。我们的研究结果表明,增强技术可以进一步改善基于MBERT的强基线。我们将字符级方法标识为最常见的表演者,而同义词替换和语法增强仪提供不一致的改进。最后,我们讨论了最大依赖于任务,语言对和模型类型的结果。
translated by 谷歌翻译
借助情境化语言模型的成功,许多研究探讨了这些模型真正学到的知识,并且在哪些情况下仍然失败。这项工作的大部分都集中在特定的NLP任务和学习成果上。很少的研究试图使模型的弱点与特定任务的弱点相结合,并专注于嵌入本身及其学习方式。在本文中,我们抓住了这一研究机会:基于理论语言见解,我们探讨了功能词的语义限制是否是学习的,以及周围环境如何影响其嵌入。我们创建合适的数据集,为LMS VIS-VIS功能单词的内部工作提供新的见解,并实施辅助视觉网络界面以进行定性分析。
translated by 谷歌翻译
预先接受训练的语言模型的进展导致了对自然语言理解的下游任务的令人印象深刻的结果。探索预先训练的语言模型的最新工作揭示了在其上下围化表示中编码的广泛的语言属性。然而,目前尚不清楚他们是否编码对符号推理方法至关重要的语义知识。我们提出了一种用于探测预先接受训练的语言模型表示的逻辑推断的语言信息的方法。我们的探测数据集涵盖主要符号推理系统所需的语言现象列表。我们发现(i)预先接受的语言模型为推断编码几种类型的语言信息,但是还有一些类型的信息弱编码,(ii)语言模型可以通过微调有效地学习语言信息缺少语言信息。总体而言,我们的调查结果提供了逻辑推理语言模型的语言信息的洞察力,以及他们的预训练程序捕获。此外,我们已经证明了语言模型作为语义和背景知识库的潜力,用于支持符号推断方法。
translated by 谷歌翻译
深层神经网络在各个领域的增殖已经增加了对这些模型的解释性的需求。沿着这条线进行的初步工作,调查了这种调查的论文集中在高级表示分析上。然而,最近的工作分支集中在这些模型中分析神经元的更详细水平上的可解释性。在本文中,我们调查了神经元分析所做的工作,包括:i)在网络中发现和理解神经元的方法,ii)评估方法,iii)主要发现,包括神经元分析已解散的跨架构比较,iv)神经元的应用。探索:控制模型,域适应等,v)关于开放问题和未来研究方向的讨论。
translated by 谷歌翻译
Targeted syntactic evaluations of language models ask whether models show stable preferences for syntactically acceptable content over minimal-pair unacceptable inputs. Most targeted syntactic evaluation datasets ask models to make these judgements with just a single context-free sentence as input. This does not match language models' training regime, in which input sentences are always highly contextualized by the surrounding corpus. This mismatch raises an important question: how robust are models' syntactic judgements in different contexts? In this paper, we investigate the stability of language models' performance on targeted syntactic evaluations as we vary properties of the input context: the length of the context, the types of syntactic phenomena it contains, and whether or not there are violations of grammaticality. We find that model judgements are generally robust when placed in randomly sampled linguistic contexts. However, they are substantially unstable for contexts containing syntactic structures matching those in the critical test content. Among all tested models (GPT-2 and five variants of OPT), we significantly improve models' judgements by providing contexts with matching syntactic structures, and conversely significantly worsen them using unacceptable contexts with matching but violated syntactic structures. This effect is amplified by the length of the context, except for unrelated inputs. We show that these changes in model performance are not explainable by simple features matching the context and the test inputs, such as lexical overlap and dependency overlap. This sensitivity to highly specific syntactic features of the context can only be explained by the models' implicit in-context learning abilities.
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
We propose reconstruction probing, a new analysis method for contextualized representations based on reconstruction probabilities in masked language models (MLMs). This method relies on comparing the reconstruction probabilities of tokens in a given sequence when conditioned on the representation of a single token that has been fully contextualized and when conditioned on only the decontextualized lexical prior of the model. This comparison can be understood as quantifying the contribution of contextualization towards reconstruction -- the difference in the reconstruction probabilities can only be attributed to the representational change of the single token induced by contextualization. We apply this analysis to three MLMs and find that contextualization boosts reconstructability of tokens that are close to the token being reconstructed in terms of linear and syntactic distance. Furthermore, we extend our analysis to finer-grained decomposition of contextualized representations, and we find that these boosts are largely attributable to static and positional embeddings at the input layer.
translated by 谷歌翻译
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
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
A machine learning system can score well on a given test set by relying on heuristics that are effective for frequent example types but break down in more challenging cases. We study this issue within natural language inference (NLI), the task of determining whether one sentence entails another. We hypothesize that statistical NLI models may adopt three fallible syntactic heuristics: the lexical overlap heuristic, the subsequence heuristic, and the constituent heuristic. To determine whether models have adopted these heuristics, we introduce a controlled evaluation set called HANS (Heuristic Analysis for NLI Systems), which contains many examples where the heuristics fail. We find that models trained on MNLI, including BERT, a state-of-the-art model, perform very poorly on HANS, suggesting that they have indeed adopted these heuristics. We conclude that there is substantial room for improvement in NLI systems, and that the HANS dataset can motivate and measure progress in this area.
translated by 谷歌翻译
Contextualized representation models such as ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2018) have recently achieved state-of-the-art results on a diverse array of downstream NLP tasks. Building on recent token-level probing work, we introduce a novel edge probing task design and construct a broad suite of sub-sentence tasks derived from the traditional structured NLP pipeline. We probe word-level contextual representations from four recent models and investigate how they encode sentence structure across a range of syntactic, semantic, local, and long-range phenomena. We find that existing models trained on language modeling and translation produce strong representations for syntactic phenomena, but only offer comparably small improvements on semantic tasks over a non-contextual baseline.
translated by 谷歌翻译
Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large version, and investigate how faithful their representations are with respect to the semantic content of texts. We formalize a notion of semantic faithfulness, in which the semantic content of a text should causally figure in a model's inferences in question answering. We then test this notion by observing a model's behavior on answering questions about a story after performing two novel semantic interventions -- deletion intervention and negation intervention. While transformer models achieve high performance on standard question answering tasks, we show that they fail to be semantically faithful once we perform these interventions for a significant number of cases (~50% for deletion intervention, and ~20% drop in accuracy for negation intervention). We then propose an intervention-based training regime that can mitigate the undesirable effects for deletion intervention by a significant margin (from ~50% to ~6%). We analyze the inner-workings of the models to better understand the effectiveness of intervention-based training for deletion intervention. But we show that this training does not attenuate other aspects of semantic unfaithfulness such as the models' inability to deal with negation intervention or to capture the predicate-argument structure of texts. We also test InstructGPT, via prompting, for its ability to handle the two interventions and to capture predicate-argument structure. While InstructGPT models do achieve very high performance on predicate-argument structure task, they fail to respond adequately to our deletion and negation interventions.
translated by 谷歌翻译