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.

大型基于变压器的预训练的语言模型在各种知识密集的任务上取得了令人印象深刻的表现，并可以在其参数中捕获事实知识。我们认为，考虑到不断增长的知识和资源需求，在模型参数中存储大量知识是亚最佳选择。我们认为，更有效的替代方法是向模型提供对上下文相关的结构化知识的明确访问，并训练它以使用该知识。我们提出了LM核 - 实现这一目标的一般框架 - 允许从外部知识源对语言模型培训的\ textit {解耦}，并允许后者更新而不会影响已经训练的模型。实验结果表明，LM核心获得外部知识，在知识探索任务上的最先进的知识增强语言模型中实现了重要而强大的优于性能。可以有效处理知识更新；并在两个下游任务上表现良好。我们还提出了一个彻底的错误分析，突出了LM核的成功和失败。

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.

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.

自动问题应答（QA）系统的目的是以时间有效的方式向用户查询提供答案。通常在数据库（或知识库）或通常被称为语料库的文件集合中找到答案。在过去的几十年里，收购知识的扩散，因此生物医学领域的新科学文章一直是指数增长。因此，即使对于领域专家，也难以跟踪域中的所有信息。随着商业搜索引擎的改进，用户可以在某些情况下键入其查询并获得最相关的一小组文档，以及在某些情况下从文档中的相关片段。但是，手动查找所需信息或答案可能仍然令人疑惑和耗时。这需要开发高效的QA系统，该系统旨在为用户提供精确和精确的答案提供了生物医学领域的自然语言问题。在本文中，我们介绍了用于开发普通域QA系统的基本方法，然后彻底调查生物医学QA系统的不同方面，包括使用结构化数据库和文本集合的基准数据集和几种提出的方​​法。我们还探讨了当前系统的局限性，并探索潜在的途径以获得进一步的进步。

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.

Natural Language Processing (NLP) has been revolutionized by the use of Pre-trained Language Models (PLMs) such as BERT. Despite setting new records in nearly every NLP task, PLMs still face a number of challenges including poor interpretability, weak reasoning capability, and the need for a lot of expensive annotated data when applied to downstream tasks. By integrating external knowledge into PLMs, \textit{\underline{K}nowledge-\underline{E}nhanced \underline{P}re-trained \underline{L}anguage \underline{M}odels} (KEPLMs) have the potential to overcome the above-mentioned limitations. In this paper, we examine KEPLMs systematically through a series of studies. Specifically, we outline the common types and different formats of knowledge to be integrated into KEPLMs, detail the existing methods for building and evaluating KEPLMS, present the applications of KEPLMs in downstream tasks, and discuss the future research directions. Researchers will benefit from this survey by gaining a quick and comprehensive overview of the latest developments in this field.

预训练的语言模型（PTLM）已显示出在自然语言任务上表现良好。许多先前的作品都以通过知识图（KGS）标记的关系链接的实体的形式利用结构性常识来协助PTLM。检索方法使用kg作为单独的静态模块，该模块限制了覆盖范围，因为kgs包含有限的知识。生成方法训练PTLMS kg三倍以提高获得知识的规模。但是，对符号KG实体的培训限制了其在涉及自然语言文本的任务中的适用性，在这些任务中，它们忽略了整体上下文。为了减轻这种情况，我们提出了一个以句子为条件的常识性上下文化器（COSE-CO）作为输入，以使其在生成与输入文本的整体上下文相关的任务中通常可用。为了训练Cose-Co，我们提出了一个新的数据集，其中包括句子和常识知识对。 COSE-CO推断出的知识是多种多样的，并且包含了基础KG中不存在的新实体。我们增强了在多选质量质量检查和开放式常识性推理任务中产生的知识，从而改善了CSQA，ARC，QASC和OBQA数据集的当前最佳方法。我们还展示了其在改善释义生成任务的基线模型方面的适用性。

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。

关于概念及其属性的常识知识（CSK）有助于AI应用程序。诸如ConceptNet之类的先前作品已经编译了大型CSK集合。但是，它们的表现力限制在主题性 - 预处理（SPO）的三联元中，对p和o的s和字符串的简单概念。与先前的作品相比，CSK断言具有精致的表现力和更好的精度和回忆。 Ascent ++通过用子组和方面捕获复合概念，以及用语义方面的主张来捕获复合概念。后者对于表达断言和进一步预选赛的时间和空间有效性至关重要。此外，Ascent ++将开放信息提取（OpenIE）与典型性和显着性分数的明智清洁和排名相结合。对于高覆盖范围，我们的方法挖掘到具有广泛的Web内容的大规模爬网C4中。通过人类判断的评估显示了上升++ Kb的卓越质量，以及对QA支持任务的外部评估强调了Ascent ++的好处。可以在https://ascentpp.mpi-inf.mpg.de/上访问Web界面，数据和代码。

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。

大型文本语料库培训的基于变压器的语言模型在自然语言处理社区中享有巨大的普及，并且通常用作下游任务的起点。虽然这些模型是不可否认的，但这是一种挑战，以量化超出传统准确度指标的性能。在本文中，我们通过在培训过程的顺序阶段的获取知识快照来比较基于BERT的语言模型。可以通过查询具有探测任务的屏蔽语言模型来发现来自培训语料库的结构化关系。我们提出了一种通过在罗伯塔早期训练的各个阶段的CLOZE“填空”陈述中产生知识图表提取物来揭示知识收集时间表的方法。我们将该分析扩展到BERT模型（Distilbert，Bert-Base，Roberta）的预磨损变体进行比较。这项工作提出了通过知识图提取（GED，Graph2VEC）来比较语言模型的定量框架，并且展示了语音分析（波动）以确定每个模型变体的语言强度。使用这些指标，机器学习从业者可以比较模型，诊断其模型的行为优势和劣势，并确定新的目标数据集以提高模型性能。

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。

关于概念及其属性的常识知识（CSK）对AI应用程序（例如强大的聊天机器人）有用。诸如ConceptNet，Tuplekb和其他人之类的先前作品汇编了大型CSK集合，但在其表现力上限制了主题性主体对象（SPO）三倍（SPO）三元组，其中s和p和Onolithic的简单概念是P和O。这些项目都优先考虑精确精度。或召回，但几乎不能调和这些互补目标。本文介绍了一种称为Ascent的方法，以自动建立一个大规模的CSK断言的知识库（KB），具有高级表现力，并且比先前的作品更好，并且具有更好的精度和回忆。通过捕获子组和方面的复合概念，以及通过语义方面的主张来捕获复合概念，超越了三倍。后者对于表达断言和进一步预选赛的时间和空间有效性很重要。 Ascent使用语言模型将开放信息提取与明智的清洁结合在一起。内在评估显示了上升KB的较高规模和质量，QA支持任务的外部评估强调了上升的好处。可以在https://ascent.mpi-inf.mpg.de/上找到Web界面，数据和代码。

Relation extraction (RE) is a sub-discipline of information extraction (IE) which focuses on the prediction of a relational predicate from a natural-language input unit (such as a sentence, a clause, or even a short paragraph consisting of multiple sentences and/or clauses). Together with named-entity recognition (NER) and disambiguation (NED), RE forms the basis for many advanced IE tasks such as knowledge-base (KB) population and verification. In this work, we explore how recent approaches for open information extraction (OpenIE) may help to improve the task of RE by encoding structured information about the sentences' principal units, such as subjects, objects, verbal phrases, and adverbials, into various forms of vectorized (and hence unstructured) representations of the sentences. Our main conjecture is that the decomposition of long and possibly convoluted sentences into multiple smaller clauses via OpenIE even helps to fine-tune context-sensitive language models such as BERT (and its plethora of variants) for RE. Our experiments over two annotated corpora, KnowledgeNet and FewRel, demonstrate the improved accuracy of our enriched models compared to existing RE approaches. Our best results reach 92% and 71% of F1 score for KnowledgeNet and FewRel, respectively, proving the effectiveness of our approach on competitive benchmarks.

Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions; and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, and visual-language generation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.

Supervised Question Answering systems (QA systems) rely on domain-specific human-labeled data for training. Unsupervised QA systems generate their own question-answer training pairs, typically using secondary knowledge sources to achieve this outcome. Our approach (called PIE-QG) uses Open Information Extraction (OpenIE) to generate synthetic training questions from paraphrased passages and uses the question-answer pairs as training data for a language model for a state-of-the-art QA system based on BERT. Triples in the form of <subject, predicate, object> are extracted from each passage, and questions are formed with subjects (or objects) and predicates while objects (or subjects) are considered as answers. Experimenting on five extractive QA datasets demonstrates that our technique achieves on-par performance with existing state-of-the-art QA systems with the benefit of being trained on an order of magnitude fewer documents and without any recourse to external reference data sources.

知识库问题应答（KBQA）旨在在外部知识库的帮助下回答自然语言问题。核心思想是找到内部知识与知识库的已知三元组之间的内部知识之间的联系。 KBQA任务管道包含几个步骤，包括实体识别，关系提取和实体链接。这种管道方法意味着任何过程中的错误将不可避免地传播到最终预测。为了解决上述问题，本文提出了一种具有预培训语言模型（PLM）和知识图（KG）的语料库生成 - 检索方法（CGRM）。首先，基于MT5模型，我们设计了两个新的预训练任务：基于段落的知识屏蔽语言建模和问题，以获取知识增强型T5（KT5）模型。其次，在用一系列启发式规则预处理知识图的预处理之后，KT5模型基于处理的三元组生成自然语言QA对。最后，我们通过检索合成数据集直接解决QA。我们在NLPCC-ICCPOL 2016 KBQA数据集上测试我们的方法，结果表明，我们的框架提高了KBQA的性能，直接向前的方法与最先进的方法竞争。

开放信息提取是一个重要的NLP任务，它针对从非结构化文本中提取结构化信息的目标，而无需限制关系类型或文本域。该调查文件涵盖了2007年至2022年的开放信息提取技术，重点是以前的调查未涵盖的新模型。我们从信息角度来源提出了一种新的分类方法，以适应最近的OIE技术的开发。此外，我们根据任务设置以及当前流行的数据集和模型评估指标总结了三种主要方法。鉴于全面的审查，从数据集，信息来源，输出表格，方法和评估指标方面显示了几个未来的方向。

与伯特（Bert）等语言模型相比，已证明知识增强语言表示的预培训模型在知识基础构建任务（即〜关系提取）中更有效。这些知识增强的语言模型将知识纳入预训练中，以生成实体或关系的表示。但是，现有方法通常用单独的嵌入表示每个实体。结果，这些方法难以代表播出的实体和大量参数，在其基础代币模型之上（即〜变压器），必须使用，并且可以处理的实体数量为由于内存限制，实践限制。此外，现有模型仍然难以同时代表实体和关系。为了解决这些问题，我们提出了一个新的预培训模型，该模型分别从图书中学习实体和关系的表示形式，并分别在文本中跨越跨度。通过使用SPAN模块有效地编码跨度，我们的模型可以代表实体及其关系，但所需的参数比现有模型更少。我们通过从Wikipedia中提取的知识图对我们的模型进行了预训练，并在广泛的监督和无监督的信息提取任务上进行了测试。结果表明，我们的模型比基线学习对实体和关系的表现更好，而在监督的设置中，微调我们的模型始终优于罗伯塔，并在信息提取任务上取得了竞争成果。