本文描述了我们对第9届论证挖掘研讨会共同任务的贡献（2022）。我们的方法使用大型语言模型来进行论证质量预测的任务。我们使用GPT-3进行及时的工程，并研究培训范式多任务学习，对比度学习和中任务培训。我们发现混合预测设置优于单个模型。提示GPT-3最适合预测论点有效性，而论证新颖性最好通过使用所有三个训练范式训练的模型来估算。

近年来，在危机期间从社交媒体职位挖掘重要信息的任务已成为辅助应急响应的目的研究的重点。 TREC事件流（IS）曲目是为此目的而组织的研究挑战。该曲目要求参与系统将与危机相关的推文进行分类为人道主义援助相关信息类型，并估算其关键性的重要性。前者是指多标签信息类型分类任务，后者是指优先级估计任务。在本文中，我们报告了TREC中的大学学院计算机科学（UCD-CS）的参与 - 是2021年。我们探讨了各种方法，包括简单的机器学习算法，多任务学习技术，文本增强和集合方法。官方评估结果表明，我们的运行达到了许多指标中的最高分数。为了援助再现性，我们的代码在HTTPS://github.com/wangcongcong123/crisis-mtl上公开提供。

大型和超大语言模型的开发，例如GPT-3，T5，Switch Transformer，Ernie等，已经显着改善了文本生成的性能。该领域的重要研究方向之一是产生具有争论的文本。该问题的解决方案可以用于商务会议，政治辩论，对话系统，以准备学生论文。这些应用的主要领域之一是经济领域。俄罗斯语言的论证文本生成的关键问题是缺乏注释的论证语料库。在本文中，我们将论证的微观版，说服力论文和UKP句子语料库的翻译版本用于微调Rubert模型。此外，该模型用于通过论证注释经济新闻的语料库。然后使用带注释的语料库微调Rugpt-3模型，该模型生成参数文本。结果表明，与原始的Rugpt-3模型相比，这种方法将论点生成的准确性提高了20个百分点（63.2 \％vs. 42.5 \％）。

This paper investigates models of event implications. Specifically, how well models predict entity state-changes, by targeting their understanding of physical attributes. Nominally, Large Language models (LLM) have been exposed to procedural knowledge about how objects interact, yet our benchmarking shows they fail to reason about the world. Conversely, we also demonstrate that existing approaches often misrepresent the surprising abilities of LLMs via improper task encodings and that proper model prompting can dramatically improve performance of reported baseline results across multiple tasks. In particular, our results indicate that our prompting technique is especially useful for unseen attributes (out-of-domain) or when only limited data is available.

Facebook和Twitter等社交媒体平台上的在线形象已成为互联网用户的日常习惯。尽管平台为用户提供了大量服务，但用户仍遭受网络欺凌的困扰，这进一步导致了精神虐待，并可能升级以对个人或目标群体造成身体伤害。在本文中，我们使用相关的阿拉伯语Twitter数据集将其提交给阿拉伯仇恨言论2022共享任务研讨会（OSACT5 2022）。共享任务由3个子任务组成，子任务A的重点是检测该推文是否令人反感。然后，对于进攻性推文，子任务B专注于检测该推文是否是仇恨言论。最后，对于仇恨言论推文，子任务C的重点是检测六个不同类别中的细粒度仇恨言论。变压器模型证明了它们在分类任务方面的效率，但是在小型或不平衡数据集中进行微调时的合适问题。我们通过研究多个培训范式（例如对比学习和多任务学习以及分类微调）以及我们前5名表演者的合奏来克服这一限制。我们提出的解决方案分别在子任务A，B和C中分别实现了0.841、0.817和0.476宏F1平均。

In this work, we explore "prompt tuning," a simple yet effective mechanism for learning "soft prompts" to condition frozen language models to perform specific downstream tasks. Unlike the discrete text prompts used by GPT-3, soft prompts are learned through backpropagation and can be tuned to incorporate signals from any number of labeled examples. Our end-to-end learned approach outperforms GPT-3's few-shot learning by a large margin. More remarkably, through ablations on model size using T5, we show that prompt tuning becomes more competitive with scale: as models exceed billions of parameters, our method "closes the gap" and matches the strong performance of model tuning (where all model weights are tuned). This finding is especially relevant because large models are costly to share and serve and the ability to reuse one frozen model for multiple downstream tasks can ease this burden. Our method can be seen as a simplification of the recently proposed "prefix tuning" of Li and Liang (2021) and we provide a comparison to this and other similar approaches. Finally, we show that conditioning a frozen model with soft prompts confers benefits in robustness to domain transfer and enables efficient "prompt ensembling." * Work done as a Google AI Resident.

The strong few-shot in-context learning capability of large pre-trained language models (PLMs) such as GPT-3 is highly appealing for application domains such as biomedicine, which feature high and diverse demands of language technologies but also high data annotation costs. In this paper, we present the first systematic and comprehensive study to compare the few-shot performance of GPT-3 in-context learning with fine-tuning smaller (i.e., BERT-sized) PLMs on two highly representative biomedical information extraction tasks, named entity recognition and relation extraction. We follow the true few-shot setting to avoid overestimating models' few-shot performance by model selection over a large validation set. We also optimize GPT-3's performance with known techniques such as contextual calibration and dynamic in-context example retrieval. However, our results show that GPT-3 still significantly underperforms compared to simply fine-tuning a smaller PLM. In addition, GPT-3 in-context learning also yields smaller gains in accuracy when more training data becomes available. Our in-depth analyses further reveal issues of the in-context learning setting that may be detrimental to information extraction tasks in general. Given the high cost of experimenting with GPT-3, we hope our study provides guidance for biomedical researchers and practitioners towards more promising directions such as fine-tuning small PLMs.

培训和评估语言模型越来越多地要求构建元数据 - 多样化的策划数据收集，并具有清晰的出处。自然语言提示最近通过将现有的，有监督的数据集转换为多种新颖的预处理任务，突出了元数据策划的好处，从而改善了零击的概括。尽管将这些以数据为中心的方法转化为生物医学语言建模的通用域文本成功，但由于标记的生物医学数据集在流行的数据中心中的代表性大大不足，因此仍然具有挑战性。为了应对这一挑战，我们介绍了BigBio一个由126个以上的生物医学NLP数据集的社区库，目前涵盖12个任务类别和10多种语言。 BigBio通过对数据集及其元数据进行程序化访问来促进可再现的元数据策划，并与当前的平台兼容，以及时工程和端到端的几个/零射击语言模型评估。我们讨论了我们的任务架构协调，数据审核，贡献指南的过程，并概述了两个说明性用例：生物医学提示和大规模，多任务学习的零射门评估。 BigBio是一项持续的社区努力，可在https://github.com/bigscience-workshop/biomedical上获得。

Traditional multi-task learning architectures train a single model across multiple tasks through a shared encoder followed by task-specific decoders. Learning these models often requires specialized training algorithms that address task-conflict in the shared parameter updates, which otherwise can lead to negative transfer. A new type of multi-task learning within NLP homogenizes multi-task architectures as a shared encoder and language model decoder, which does surprisingly well across a range of diverse tasks. Does this new architecture suffer from task-conflicts that require specialized training algorithms? We study how certain factors in the shift towards text-to-text models affects multi-task conflict and negative transfer, finding that both directional conflict and transfer are surprisingly constant across architectures.

Handling and digesting a huge amount of information in an efficient manner has been a long-term demand in modern society. Some solutions to map key points (short textual summaries capturing essential information and filtering redundancies) to a large number of arguments/opinions have been provided recently (Bar-Haim et al., 2020). To complement the full picture of the argument-to-keypoint mapping task, we mainly propose two approaches in this paper. The first approach is to incorporate prompt engineering for fine-tuning the pre-trained language models (PLMs). The second approach utilizes prompt-based learning in PLMs to generate intermediary texts, which are then combined with the original argument-keypoint pairs and fed as inputs to a classifier, thereby mapping them. Furthermore, we extend the experiments to cross/in-domain to conduct an in-depth analysis. In our evaluation, we find that i) using prompt engineering in a more direct way (Approach 1) can yield promising results and improve the performance; ii) Approach 2 performs considerably worse than Approach 1 due to the negation issue of the PLM.

姿态检测的目标是确定以目标朝向目标的文本中表达的视点。这些观点或上下文通常以许多不同的语言表达，这取决于用户和平台，这可以是本地新闻插座，社交媒体平台，新闻论坛等。然而，姿态检测的大多数研究已经限于使用单一语言和几个有限的目标，在交叉舌姿态检测很少有效。此外，标记数据的非英语来源通常稀缺，并具有额外的挑战。最近，大型多语言语言模型在许多非英语任务上大大提高了性能，尤其是具有有限数量的示例。这突出了模型预培训的重要性及其从少数例子中学习的能力。在本文中，我们展示了对日期交叉姿态检测的最全面的研究：我们在6名语言系列中使用12种语言的12种不同的数据集进行实验，每个都有6个低资源评估设置。对于我们的实验，我们构建了模式开发培训，提出了添加一种新颖的标签编码器来简化言语程序。我们进一步提出了基于情绪的姿态数据进行预培训，这在与几个强的基线相比，在低拍摄环境中显示了大量的6％F1绝对的增长。

论证分析是一个计算语言学领域，该领域研究了从文本及其之间的关系中提取参数的方法以及文本的论证结构。本文是组织者关于在对话会议框架内涉及俄罗斯语言文本的第一个论证分析系统竞争的报告。在比赛期间，参与者得到了两项任务：立场检测和论证分类。准备了与Covid-19-19的大流行有关的三个主题（疫苗接种，隔离和戴口罩）的三个主题的语料库（有关社交媒体帖子的评论），并进行了注释，并用于培训和测试。在这两个任务中赢得第一名的系统都使用了BERT体系结构的NLI（自然语言推理）变体，自动翻译为英语以应用专业的BERT模型，在Twitter帖子上进行了讨论COVID-19，以及对COVID-19目标实体。该系统显示以下结果：对于立场检测任务，F1得分为0.6968，对于参数分类任务，F1得分为0.7404。我们希望准备好的数据集和基线将有助于进一步研究俄罗斯语言的论证挖掘。

We introduce TeSS (Text Similarity Comparison using Sentence Encoder), a framework for zero-shot classification where the assigned label is determined by the embedding similarity between the input text and each candidate label prompt. We leverage representations from sentence encoders optimized to locate semantically similar samples closer to each other in embedding space during pre-training. The label prompt embeddings serve as prototypes of their corresponding class clusters. Furthermore, to compensate for the potentially poorly descriptive labels in their original format, we retrieve semantically similar sentences from external corpora and additionally use them with the original label prompt (TeSS-R). TeSS outperforms strong baselines on various closed-set and open-set classification datasets under zero-shot setting, with further gains when combined with label prompt diversification through retrieval. These results are robustly attained to verbalizer variations, an ancillary benefit of using a bi-encoder. Altogether, our method serves as a reliable baseline for zero-shot classification and a simple interface to assess the quality of sentence encoders.

在这项工作中，我们介绍了患者生成的含量中第一个用于德国不良药物反应（ADR）检测的语料库。该数据包括来自德国患者论坛的4,169个二进制注释的文档，用户谈论健康问题并从医生那里获得建议。正如该领域的社交媒体数据中常见的那样，语料库的类标签非常不平衡。这一主题不平衡使其成为一个非常具有挑战性的数据集，因为通常相同的症状可能会有几种原因，并且并不总是与药物摄入有关。我们旨在鼓励在ADR检测领域进行进一步的多语性努力，并使用基于多语言模型的零和少数学习方法为二进制分类提供初步实验。当对XLM-Roberta进行微调首先在英语患者论坛数据上，然后在新的德国数据上进行微调时，我们的正面级别的F1得分为37.52。我们使数据集和模型公开可供社区使用。

文本匹配是信息检索和自然语言处理的基本技术。文本匹配任务共享确定两个给定文本之间关系的相同范例。这些关系因任务而异，例如〜在文档检索中相关性，释义识别中的语义一致性和所回答的可回答判断。但是，文本匹配的基本信号保留在有限范围中，即〜精确匹配，语义匹配和推理匹配。理想情况下，良好的文本匹配模型可以学会捕获和汇总这些信号，以实现不同的匹配任务以实现竞争性能，而最近的最新文本匹配模型，例如〜预训练的语言模型（PLM）很难概括。这是因为在特定于任务的数据集上的端到端监督学习使模型过分强调了数据示例偏置和特定于任务的信号，而不是基本的匹配信号。为了克服这个问题，我们采用了专业化的将军培训策略，并将其称为比赛推出。在专业阶段，对不同匹配任务的描述映射到一些提示令牌。在概括阶段，匹配模型通过接受各种匹配任务的培训来探索基本匹配信号。高不同的匹配任务避免了模型拟合特定任务的数据偏差，因此该模型可以专注于学习基本匹配信号。同时，在第一步中获得的提示令牌有助于模型区分不同的特定任务匹配信号。公共数据集上的实验结果表明，匹配点可以提高PLM在文本匹配中的多任务概括能力，并产生更好的内域多任务，外域多任务和新任务适应性性能由以前的微调范式训练的特定于任务模型。

Laws and their interpretations, legal arguments and agreements\ are typically expressed in writing, leading to the production of vast corpora of legal text. Their analysis, which is at the center of legal practice, becomes increasingly elaborate as these collections grow in size. Natural language understanding (NLU) technologies can be a valuable tool to support legal practitioners in these endeavors. Their usefulness, however, largely depends on whether current state-of-the-art models can generalize across various tasks in the legal domain. To answer this currently open question, we introduce the Legal General Language Understanding Evaluation (LexGLUE) benchmark, a collection of datasets for evaluating model performance across a diverse set of legal NLU tasks in a standardized way. We also provide an evaluation and analysis of several generic and legal-oriented models demonstrating that the latter consistently offer performance improvements across multiple tasks.

数据增强是通过转换为机器学习的人工创建数据的人工创建，是一个跨机器学习学科的研究领域。尽管它对于增加模型的概括功能很有用，但它还可以解决许多其他挑战和问题，从克服有限的培训数据到正规化目标到限制用于保护隐私的数据的数量。基于对数据扩展的目标和应用的精确描述以及现有作品的分类法，该调查涉及用于文本分类的数据增强方法，并旨在为研究人员和从业者提供简洁而全面的概述。我们将100多种方法划分为12种不同的分组，并提供最先进的参考文献来阐述哪种方法可以通过将它们相互关联，从而阐述了哪种方法。最后，提供可能构成未来工作的基础的研究观点。

Reasoning is central to human intelligence. However, fallacious arguments are common, and some exacerbate problems such as spreading misinformation about climate change. In this paper, we propose the task of logical fallacy detection, and provide a new dataset (Logic) of logical fallacies generally found in text, together with an additional challenge set for detecting logical fallacies in climate change claims (LogicClimate). Detecting logical fallacies is a hard problem as the model must understand the underlying logical structure of the argument. We find that existing pretrained large language models perform poorly on this task. In contrast, we show that a simple structure-aware classifier outperforms the best language model by 5.46% on Logic and 4.51% on LogicClimate. We encourage future work to explore this task as (a) it can serve as a new reasoning challenge for language models, and (b) it can have potential applications in tackling the spread of misinformation. Our dataset and code are available at https://github.com/causalNLP/logical-fallacy

索赔检测和验证对于新闻认识至关重要，并且已成为有前途的技术，以减轻新闻中的错误信息。然而，大多数现有的工作侧重于索赔句子的分析，同时俯瞰关键背景属性，例如索引者，声称对象和连接到索赔的其他知识。在这项工作中，我们提供了新闻本，新的基准，了解新闻领域的知识意识索赔检测。我们重新定义了索赔探测问题，包括提取与索赔相关的附加背景属性，并发布529索赔由103个新闻文章提示。此外，报讯人旨在在新兴场景中索取索赔检测系统，包括不少培训数据的看不见的主题。最后，我们对这款新基准测试提供了对各种零射和及时的基础基准的全面评估。

法律文件是非结构化的，使用法律术语，并且具有相当长的长度，使得难以通过传统文本处理技术自动处理。如果文档可以在语义上分割成连贯的信息单位，法律文件处理系统将基本上受益。本文提出了一种修辞职位（RR）系统，用于将法律文件分组成语义连贯的单位：事实，论点，法规，问题，先例，裁决和比例。在法律专家的帮助下，我们提出了一套13个细粒度的修辞标志标签，并创建了与拟议的RR批发的新的法律文件有条件。我们开发一个系统，以将文件分段为修辞职位单位。特别是，我们开发了一种基于多任务学习的深度学习模型，文档修辞角色标签作为分割法律文件的辅助任务。我们在广泛地尝试各种深度学习模型，用于预测文档中的修辞角色，并且所提出的模型对现有模型显示出卓越的性能。此外，我们应用RR以预测法律案件的判断，并表明与基于变压器的模型相比，使用RR增强了预测。