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。

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。

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.

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.

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.

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。

This paper investigates the ability of artificial neural networks to judge the grammatical acceptability of a sentence, with the goal of testing their linguistic competence. We introduce the Corpus of Linguistic Acceptability (CoLA), a set of 10,657 English sentences labeled as grammatical or ungrammatical from published linguistics literature. As baselines, we train several recurrent neural network models on acceptability classification, and find that our models outperform unsupervised models by Lau et al. (2016) on CoLA. Error-analysis on specific grammatical phenomena reveals that both Lau et al.'s models and ours learn systematic generalizations like subject-verb-object order. However, all models we test perform far below human level on a wide range of grammatical constructions.

当前的语言模型可以产生高质量的文本。他们只是复制他们之前看到的文本，或者他们学习了普遍的语言抽象吗？要取笑这些可能性，我们介绍了乌鸦，这是一套评估生成文本的新颖性，专注于顺序结构（n-gram）和句法结构。我们将这些分析应用于四种神经语言模型（LSTM，变压器，变换器-XL和GPT-2）。对于本地结构 - 例如，单个依赖性 - 模型生成的文本比来自每个模型的测试集的人类生成文本的基线显着不那么新颖。对于大规模结构 - 例如，总句结构 - 模型生成的文本与人生成的基线一样新颖甚至更新颖，但模型仍然有时复制，在某些情况下，在训练集中重复超过1000字超过1,000字的通道。我们还表现了广泛的手动分析，表明GPT-2的新文本通常在形态学和语法中形成良好，但具有合理的语义问题（例如，是自相矛盾）。

虽然句子异常已经定期应用于NLP中的测试，但我们尚未建立从NLP模型中的表示中的异常信息的确切状态的图片。在本文中，我们的目标是填补两个主要间隙，重点关注句法异常的领域。首先，我们通过设计改变异常在句子中发生的分层级别的探测任务来探讨异常编码的细粒度差异。其次，我们不仅测试了模型能够通过检查不同异常类型之间的转移来检测给定异常的能力，还能检测给定的异常信号的一般性。结果表明，所有型号都编码一些支持异常检测的信息，但检测性能在异常之间变化，并且只有最近的变压器模型的唯一表示显示了异常知识的概括知识的迹象。随访分析支持这些模型在合法的句子奇迹上接受合法的概念，而粗糙的单词位置信息也可能是观察到的异常检测的贡献者。

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。

自然语言处理（NLP）已成为当前人工智能繁荣中的主要应用领域之一。转移学习已经启用了大量深入学习的神经网络，接受了语言建模任务，以大大提高了所有语言任务的性能。有趣的是，当模型培训使用包含软件代码的数据培训时，它们在从自然语言规范中生成功能计算机代码时展示了显着的能力。我们认为这是一种难题，用于神经模型为生成词组结构语法提供了一种替代理论，以说明语言有效。由于编程语言的语法由短语结构语法决定，因此成功的神经模型显然是对编程语言的理论基础的理论基础，以及通过扩展，自然语言来实现。我们认为语言模型的术语模型是误导性的，因为深度学习模型不是语言的理论模型，并提出采用语料库模型，这更好地反映了模型的成因和内容。

语法提示有时具有自然语言的单词含义。例如，英语单词顺序规则限制了句子的单词顺序，例如“狗咀嚼骨头”，即使可以从世界知识和合理性中推断出“狗”作为代理人和“骨头”的状态。量化这种冗余的发生频率，以及冗余水平如何在类型上多样化的语言中变化，可以阐明语法的功能和演变。为此，我们在英语和俄语中进行了一个行为实验，并进行了跨语言计算分析，以测量从自然主义文本中提取的及物子句中语法线索的冗余性。从自然发生的句子中提取的主题，动词和物体（按随机顺序和形态标记）提出了英语和俄罗斯说话者（n = 484），并被要求确定哪个名词是该动作的推动者。两种语言的准确性都很高（英语约为89％，俄语为87％）。接下来，我们在类似的任务上训练了神经网络机分类器：预测主题对象三合会中的哪个名义是主题。在来自八个语言家庭的30种语言中，性能始终很高：中位准确性为87％，与人类实验中观察到的准确性相当。结论是，语法提示（例如单词顺序）对于仅在10-15％的自然句子中传达了代理和耐心是必要的。然而，他们可以（a）提供重要的冗余来源，（b）对于传达无法从单词中推断出的预期含义至关重要，包括对人类互动的描述，在这些含义中，角色通常是可逆的（例如，雷（Ray）帮助lu/ Lu帮助雷），表达了非典型的含义（例如，“骨头咀嚼狗”。）。

This work presents a detailed linguistic analysis into why larger Transformer-based pre-trained language models with more parameters and lower perplexity nonetheless yield surprisal estimates that are less predictive of human reading times. First, regression analyses show a strictly monotonic, positive log-linear relationship between perplexity and fit to reading times for the more recently released five GPT-Neo variants and eight OPT variants on two separate datasets, replicating earlier results limited to just GPT-2 (Oh et al., 2022). Subsequently, analysis of residual errors reveals a systematic deviation of the larger variants, such as underpredicting reading times of named entities and making compensatory overpredictions for reading times of function words such as modals and conjunctions. These results suggest that the propensity of larger Transformer-based models to 'memorize' sequences during training makes their surprisal estimates diverge from humanlike expectations, which warrants caution in using pre-trained language models to study human language processing.

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。

人类和神经语言模型都能够执行主题 - 动词数协议（SVA）。原则上，语义不应干扰此任务，这仅需要句法知识。在这项工作中，我们测试含义是否干扰了各种复杂性的句法结构中的英语一致性。为此，我们同时生成语义上良好的和荒谬的项目。我们将Bert Base与人类的表现进行了比较，该表现是通过心理语言在线众包实验获得的。我们发现伯特和人类都对我们的语义操纵敏感：出现荒谬的项目时，它们的频率更高，尤其是当它们的句法结构具有吸引子（主题和动词之间的名词短语和与该数字不同的名词短语）时主题）。我们还发现，有意义性对SVA错误的影响对于BERT而言比对人类的影响更强，显示前者对这项任务的词汇敏感性更高。

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.

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.

我们研究了原则上的程度，原则上，语言图表表示可以补充和改进神经语言建模。通过一个由7种不同的形式主义之一的预磨削变压器和地面真相图组成的集合设置，我们发现，总体而言，语义构成结构对语言建模性能最有用 - 超越句法选区结构以及句法和语义依赖结构。此外，效果取决于语音级别的级别大大变化。总而言之，我们的调查结果指出了神经象征性语言建模的有希望的趋势，并邀请未来的研究量化不同形式主义所制作的设计选择。

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.

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.