When trained on language data, do transformers learn some arbitrary computation that utilizes the full capacity of the architecture or do they learn a simpler, tree-like computation, hypothesized to underlie compositional meaning systems like human languages? There is an apparent tension between compositional accounts of human language understanding, which are based on a restricted bottom-up computational process, and the enormous success of neural models like transformers, which can route information arbitrarily between different parts of their input. One possibility is that these models, while extremely flexible in principle, in practice learn to interpret language hierarchically, ultimately building sentence representations close to those predictable by a bottom-up, tree-structured model. To evaluate this possibility, we describe an unsupervised and parameter-free method to \emph{functionally project} the behavior of any transformer into the space of tree-structured networks. Given an input sentence, we produce a binary tree that approximates the transformer's representation-building process and a score that captures how "tree-like" the transformer's behavior is on the input. While calculation of this score does not require training any additional models, it provably upper-bounds the fit between a transformer and any tree-structured approximation. Using this method, we show that transformers for three different tasks become more tree-like over the course of training, in some cases unsupervisedly recovering the same trees as supervised parsers. These trees, in turn, are predictive of model behavior, with more tree-like models generalizing better on tests of compositional generalization.

在本文中，我们试图通过引入深度学习模型的句法归纳偏见来建立两所学校之间的联系。我们提出了两个归纳偏见的家族，一个家庭用于选区结构，另一个用于依赖性结构。选区归纳偏见鼓励深度学习模型使用不同的单位（或神经元）分别处理长期和短期信息。这种分离为深度学习模型提供了一种方法，可以从顺序输入中构建潜在的层次表示形式，即更高级别的表示由高级表示形式组成，并且可以分解为一系列低级表示。例如，在不了解地面实际结构的情况下，我们提出的模型学会通过根据其句法结构组成变量和运算符的表示来处理逻辑表达。另一方面，依赖归纳偏置鼓励模型在输入序列中找到实体之间的潜在关系。对于自然语言，潜在关系通常被建模为一个定向依赖图，其中一个单词恰好具有一个父节点和零或几个孩子的节点。将此约束应用于类似变压器的模型之后，我们发现该模型能够诱导接近人类专家注释的有向图，并且在不同任务上也优于标准变压器模型。我们认为，这些实验结果为深度学习模型的未来发展展示了一个有趣的选择。

We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are implemented through a special attention mask and deterministic transformation of the linearized tree. We find that TGs outperform various strong baselines on sentence-level language modeling perplexity, as well as on multiple syntax-sensitive language modeling evaluation metrics. Additionally, we find that the recursive syntactic composition bottleneck which represents each sentence as a single vector harms perplexity on document-level language modeling, providing evidence that a different kind of memory mechanism -- one that is independent of composed syntactic representations -- plays an important role in current successful models of long text.

通常认为语言模型能够编码语法[Tenney等，2019； Jawahar等，2019； Hewitt和Manning，2019]。在本文中，我们提出了UPOA，这是一种无监督的组成分析模型，该模型仅基于以验证的语言模型学习为跨度分割的句法距离，仅基于自我发挥的权重矩阵来计算出OUT关联得分。我们进一步提出了一个增强的版本UPIO，该版本利用了内部关联和外部关联得分来估计跨度的可能性。使用UPOA和UPIO的实验揭示了自我注意机制中查询和密钥的线性投影矩阵在解析中起重要作用。因此，我们将无监督的模型扩展到了几个射击模型（FPOA，FPIO），这些模型使用一些注释的树来学习更好的线性投影矩阵进行解析。宾夕法尼亚河岸上的实验表明，我们的无监督解析模型UPIO实现了与短句子（长度<= 10）相当的结果。我们的几个解析模型FPIO接受了仅20棵带注释的树木的训练，优于前几种镜头解析方法，该方法接受了50棵带注释的树木的训练。交叉解析的实验表明，无监督和少数解析方法都比SPMRL大多数语言的先前方法都更好[Seddah等，2013]。

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。

Compositional generalization is a basic mechanism in human language learning, which current neural networks struggle with. A recently proposed Disentangled sequence-to-sequence model (Dangle) shows promising generalization capability by learning specialized encodings for each decoding step. We introduce two key modifications to this model which encourage more disentangled representations and improve its compute and memory efficiency, allowing us to tackle compositional generalization in a more realistic setting. Specifically, instead of adaptively re-encoding source keys and values at each time step, we disentangle their representations and only re-encode keys periodically, at some interval. Our new architecture leads to better generalization performance across existing tasks and datasets, and a new machine translation benchmark which we create by detecting naturally occurring compositional patterns in relation to a training set. We show this methodology better emulates real-world requirements than artificial challenges.

超过三十年，研究人员已经开发和分析了潜伏树诱导的方法作为无监督句法解析的方法。尽管如此，与其监督的对应物相比，现代系统仍然不足以使其具有任何实际用途作为文本的结构注释。在这项工作中，我们提出了一种技术，该技术以跨度约束（即短语包围）的形式使用远端监督，以提高在无监督选项解析中的性能。使用相对少量的跨度约束，我们可以大大提高Diora的输出，这是一个已经竞争的无监督解析系统。与完整的解析树注释相比，可以通过最小的努力来获取跨度约束，例如使用从维基百科派生的词典，以查找确切的文本匹配。我们的实验显示了基于实体的跨度约束，提高了英语WSJ Penn TreeBank的选区分析超过5 F1。此外，我们的方法延伸到跨度约束易于实现的任何域，以及作为一个案例研究，我们通过从工艺数据集解析生物医学文本来证明其有效性。

虽然以完全可差异的模型的端到端学习在自然语言过程（NLP）和机器学习中取得了巨大的成功，但最近的近期兴趣与潜在的离散结构一起学习以改善最新的最终任务性能和更好的归纳偏差更好的解释性。然而，该范例并不直接地适应主流梯度的优化方法。这项工作调查了三个主要的方法来学习此类模型：通过采样，替代梯度，连续放松和边缘似然最大化。我们结束了对这些方法的应用以及检查他们诱导的学习潜在结构的检查。

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.

Deep Learning and Machine Learning based models have become extremely popular in text processing and information retrieval. However, the non-linear structures present inside the networks make these models largely inscrutable. A significant body of research has focused on increasing the transparency of these models. This article provides a broad overview of research on the explainability and interpretability of natural language processing and information retrieval methods. More specifically, we survey approaches that have been applied to explain word embeddings, sequence modeling, attention modules, transformers, BERT, and document ranking. The concluding section suggests some possible directions for future research on this topic.

诸如变形金刚和LSTMS之类的流行模型将令牌用作其信息单位。也就是说，每个令牌都被编码为向量表示，这些向量直接在计算中使用。但是，人类经常考虑跨令牌（即短语）而不是其组成代币。在本文中，我们介绍了TreeFormer，这是一个受CKY算法和变压器启发的体系结构，该体系结构学习了组成操作员和汇总功能，以构建针对短语和句子的层次编码。我们的广泛实验证明了将层次结构纳入变压器的好处，并且与机器翻译，抽象性摘要和各种自然语言理解任务相比，与基线变压器相比显示出重大改进。

诱导顺序数据的潜在树结构是今天NLP研究景观的新出现趋势，主要是由最近的方法（如Gumbel LSTM和有序神经元）（LSTM）所普及。本文提出了Fasttrees，一种新的通用神经模块，用于快速序列编码。与最先前的作品不同，考虑到树归类所需的复发，我们的工作探讨了并行树归纳的概念，即，通过分层电感偏置的并行，非自动增加时尚的分层感应偏差。为此，我们提出的Fasttrees在四个建立良好的序列建模任务中实现了对LSTM的竞争或卓越的性能，即语言建模，逻辑推断，情感分析和自然语言推断。此外，我们表明FastTrees模块可以应用于增强变压器模型，实现三个序列转换任务（机器翻译，主语 - 动词协议和数学语言理解）实现性能增益，为模块化树感应模块铺平了道路。总的来说，我们以+ 4％的逻辑推理任务和数学语言理解+ 8％的现有最先进的模型。

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。

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。

The word alignment task, despite its prominence in the era of statistical machine translation (SMT), is niche and under-explored today. In this two-part tutorial, we argue for the continued relevance for word alignment. The first part provides a historical background to word alignment as a core component of the traditional SMT pipeline. We zero-in on GIZA++, an unsupervised, statistical word aligner with surprising longevity. Jumping forward to the era of neural machine translation (NMT), we show how insights from word alignment inspired the attention mechanism fundamental to present-day NMT. The second part shifts to a survey approach. We cover neural word aligners, showing the slow but steady progress towards surpassing GIZA++ performance. Finally, we cover the present-day applications of word alignment, from cross-lingual annotation projection, to improving translation.

Syntax is a latent hierarchical structure which underpins the robust and compositional nature of human language. An active line of inquiry is whether large pretrained language models (LLMs) are able to acquire syntax by training on text alone; understanding a model's syntactic capabilities is essential to understanding how it processes and makes use of language. In this paper, we propose a new method, SSUD, which allows for the induction of syntactic structures without supervision from gold-standard parses. Instead, we seek to define formalism-agnostic, model-intrinsic syntactic parses by using a property of syntactic relations: syntactic substitutability. We demonstrate both quantitative and qualitative gains on dependency parsing tasks using SSUD, and induce syntactic structures which we hope provide clarity into LLMs and linguistic representations, alike.

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.

Large pre-trained neural networks such as BERT have had great recent success in NLP, motivating a growing body of research investigating what aspects of language they are able to learn from unlabeled data. Most recent analysis has focused on model outputs (e.g., language model surprisal) or internal vector representations (e.g., probing classifiers). Complementary to these works, we propose methods for analyzing the attention mechanisms of pre-trained models and apply them to BERT. BERT's attention heads exhibit patterns such as attending to delimiter tokens, specific positional offsets, or broadly attending over the whole sentence, with heads in the same layer often exhibiting similar behaviors. We further show that certain attention heads correspond well to linguistic notions of syntax and coreference. For example, we find heads that attend to the direct objects of verbs, determiners of nouns, objects of prepositions, and coreferent mentions with remarkably high accuracy. Lastly, we propose an attention-based probing classifier and use it to further demonstrate that substantial syntactic information is captured in BERT's attention. 1 Code will be released at https://github.com/ clarkkev/attention-analysis.2 We use the English base-sized model.

深度学习模型概括到分销数据很好，但扭动概括为合作方式，即结合一组学习的原语来解决更复杂的任务。以顺序到序列（SEQ2SEQ）学习，变压器通常无法预测比在训练中看到的更长示例的正确输出。本文介绍了迭代解码，SEQ2SEQ的替代方案（i）改善了PCFG和笛卡尔产品数据集中的变压器组成概括和（ii）在这些数据集中的证据中，SEQ2Seq变压器不学习未展开的迭代。在迭代解码中，训练示例被分解为变压器迭代地学习的一系列中间步骤。在推断时间下，中间输出被馈送回变压器，直到预测迭代令牌结束令牌。我们通过说明CFQ数据集中的迭代解码的一些限制来得出结论。

Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence length due to their full attention mechanism. To remedy this, we propose, BIGBIRD, a sparse attention mechanism that reduces this quadratic dependency to linear. We show that BIGBIRD is a universal approximator of sequence functions and is Turing complete, thereby preserving these properties of the quadratic, full attention model. Along the way, our theoretical analysis reveals some of the benefits of having O(1) global tokens (such as CLS), that attend to the entire sequence as part of the sparse attention mechanism. The proposed sparse attention can handle sequences of length up to 8x of what was previously possible using similar hardware. As a consequence of the capability to handle longer context, BIGBIRD drastically improves performance on various NLP tasks such as question answering and summarization. We also propose novel applications to genomics data.