自然语言推论（NLI）是生产人类语言有用模型的重要任务。不幸的是，大规模的NLI DataSet生产依赖于人群，倾向于在他们写的句子中引入偏见。特别地，没有质量控制，他们产生假设可以预测关系标签，而没有前提，而不是机会。我们介绍了一个模型驱动的无监督技术，可以在NLI数据集的假设中的学习嵌入空间中找到“偏置群集”，可以从哪些干预和额外的标签来执行，以改善数据集的假设分布的语义偏差。

建筑聊天禁令的最大挑战是培训数据。所需的数据必须逼真，足以训练聊天禁止。我们创建一个工具，用于从Facebook页面的Facebook Messenger获取实际培训数据。在文本预处理步骤之后，新获得的数据集生成FVNC和示例数据集。我们使用返回越南（Phobert）的伯特来提取文本数据的功能。 K-means和DBSCAN聚类算法用于基于Phobert $ _ {Base} $的输出嵌入式群集任务。我们应用V测量分数和轮廓分数来评估聚类算法的性能。我们还展示了Phobert的效率与样本数据集和Wiki DataSet上的特征提取中的其他模型相比。还提出了一种结合聚类评估的GridSearch算法来找到最佳参数。由于群集如此多的对话，我们节省了大量的时间和精力来构建培训Chatbot的数据和故事情节。

任务嵌入式是培训以捕获任务属性的低维表示。在本文中，我们提出了Metaeval，一系列101美元的NLP任务。我们将单个变压器与所有Metaeval任务联系在一起，同时将其调制到学习嵌入。由此产生的任务嵌入物能够对任务空间进行新颖分析。然后，我们显示任务方面可以映射到任务嵌入式的任务嵌入式，以用于新任务，而无需使用任何注释的示例。预测嵌入物可以调制编码器以进行零拍摄推断，并优于胶水任务上的零拍摄基线。提供的多任务设置可以用作未来转移学习研究的基准。

Current state-of-the-art approaches to text classification typically leverage BERT-style Transformer models with a softmax classifier, jointly fine-tuned to predict class labels of a target task. In this paper, we instead propose an alternative training objective in which we learn task-specific embeddings of text: our proposed objective learns embeddings such that all texts that share the same target class label should be close together in the embedding space, while all others should be far apart. This allows us to replace the softmax classifier with a more interpretable k-nearest-neighbor classification approach. In a series of experiments, we show that this yields a number of interesting benefits: (1) The resulting order induced by distances in the embedding space can be used to directly explain classification decisions. (2) This facilitates qualitative inspection of the training data, helping us to better understand the problem space and identify labelling quality issues. (3) The learned distances to some degree generalize to unseen classes, allowing us to incrementally add new classes without retraining the model. We present extensive experiments which show that the benefits of ante-hoc explainability and incremental learning come at no cost in overall classification accuracy, thus pointing to practical applicability of our proposed approach.

使用机器学习算法从未标记的文本中提取知识可能很复杂。文档分类和信息检索是两个应用程序，可以从无监督的学习（例如文本聚类和主题建模）中受益，包括探索性数据分析。但是，无监督的学习范式提出了可重复性问题。初始化可能会导致可变性，具体取决于机器学习算法。此外，关于群集几何形状，扭曲可能会产生误导。在原因中，异常值和异常的存在可能是决定因素。尽管初始化和异常问题与文本群集和主题建模相关，但作者并未找到对它们的深入分析。这项调查提供了这些亚地区的系统文献综述（2011-2022），并提出了共同的术语，因为类似的程序具有不同的术语。作者描述了研究机会，趋势和开放问题。附录总结了与审查的作品直接或间接相关的文本矢量化，分解和聚类算法的理论背景。

Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation learning, while being more interpretable in their predictions. In this paper, we develop a topic-informed discrete latent variable model for semantic textual similarity, which learns a shared latent space for sentence-pair representation via vector quantization. Compared with previous models limited to local semantic contexts, our model can explore richer semantic information via topic modeling. We further boost the performance of semantic similarity by injecting the quantized representation into a transformer-based language model with a well-designed semantic-driven attention mechanism. We demonstrate, through extensive experiments across various English language datasets, that our model is able to surpass several strong neural baselines in semantic textual similarity tasks.

我们研究了掩盖语言模型（MLMS）的任务无关内在和特定于任务的外在社会偏见评估措施之间的关系，并发现这两种评估措施之间仅存在弱相关性。此外，我们发现在下游任务进行微调期间，使用不同方法的MLMS DEBIAS进行了重新划分。我们确定两个培训实例中的社会偏见及其分配的标签是内在偏见评估测量值之间差异的原因。总体而言，我们的发现突出了现有的MLM偏见评估措施的局限性，并提出了使用这些措施在下游应用程序中部署MLM的担忧。

各种现有研究分析了NLP模型继承了哪些社会偏见。这些偏见可能直接或间接损害人们，因此以前的研究仅关注人类属性。但是，直到最近，还没有关于NLP关于非人类的社会偏见的研究。在本文中，我们分析了非人类动物的偏见，即物种主义偏见，在英语蒙面语言模型（例如Bert）中固有的偏见。我们使用基于模板的和语料库提取的句子（或非特征主义）语言分析了物种主义对46个动物名称的偏见。我们发现，预先训练的蒙版语言模型倾向于将有害单词与非人类动物联系起来，并且有偏见的偏见，将物种主义语言用于某些非人类动物名称。我们用于复制实验的代码将在GitHub上提供。

已知自然语言推断（NLI）模型从训练数据内的偏见和人工制品中学习，影响他们概括到其他看不见的数据集。现有的去偏置方法侧重于防止模型学习这些偏差，这可能导致限制模型和较低的性能。相反，我们调查教学模型如何将人类接近NLI任务，以便学习将更好地概括到以前看不见的特征。使用自然语言解释，我们监督模型的注意力，以鼓励更多地关注解释中存在的词语，显着提高模型性能。我们的实验表明，这种方法的分布式改进也伴随着分发的改进，监督模型从概括到其他NLI数据集的功能。该模型的分析表明，人类解释鼓励增加对重要词语的关注，在前提下的单词和较少关注标点符号和止扰言论的关注。

句子嵌入方法有许多成功的应用。但是，根据监督信号，在结果句子嵌入中捕获了哪些属性。在本文中，我们专注于具有相似体系结构和任务的两种类型的嵌入方法：一种关于自然语言推理任务的微型预训练的语言模型，以及其他微型训练的训练语言模型在单词预测任务上根据其定义句子，并研究其属性。具体而言，我们使用两个角度分区的STS数据集比较他们在语义文本相似性（STS）任务上的性能：1）句子源和2）句子对的表面相似性，并在下游和探测任务上比较其表现。此外，我们尝试结合两种方法，并证明将两种方法组合起来比无监督的STS任务和下游任务的各自方法的性能要好得多。

Text clustering and topic extraction are two important tasks in text mining. Usually, these two tasks are performed separately. For topic extraction to facilitate clustering, we can first project texts into a topic space and then perform a clustering algorithm to obtain clusters. To promote topic extraction by clustering, we can first obtain clusters with a clustering algorithm and then extract cluster-specific topics. However, this naive strategy ignores the fact that text clustering and topic extraction are strongly correlated and follow a chicken-and-egg relationship. Performing them separately fails to make them mutually benefit each other to achieve the best overall performance. In this paper, we propose an unsupervised text clustering and topic extraction framework (ClusTop) which integrates text clustering and topic extraction into a unified framework and can achieve high-quality clustering result and extract topics from each cluster simultaneously. Our framework includes four components: enhanced language model training, dimensionality reduction, clustering and topic extraction, where the enhanced language model can be viewed as a bridge between clustering and topic extraction. On one hand, it provides text embeddings with a strong cluster structure which facilitates effective text clustering; on the other hand, it pays high attention on the topic related words for topic extraction because of its self-attention architecture. Moreover, the training of enhanced language model is unsupervised. Experiments on two datasets demonstrate the effectiveness of our framework and provide benchmarks for different model combinations in this framework.

大多数无监督的NLP模型代表了语义空间中单点或单个区域的每个单词，而现有的多感觉单词嵌入物不能代表像素序或句子等更长的单词序列。我们提出了一种用于文本序列（短语或句子）的新型嵌入方法，其中每个序列由一个不同的多模码本嵌入物组表示，以捕获其含义的不同语义面。码本嵌入式可以被视为集群中心，该中心总结了在预训练的单词嵌入空间中的可能共同出现的单词的分布。我们介绍了一个端到端的训练神经模型，直接从测试时间内从输入文本序列预测集群中心集。我们的实验表明，每句话码本嵌入式显着提高无监督句子相似性和提取摘要基准的性能。在短语相似之处实验中，我们发现多面嵌入物提供可解释的语义表示，但不优于单面基线。

Realizing when a model is right for a wrong reason is not trivial and requires a significant effort by model developers. In some cases, an input salience method, which highlights the most important parts of the input, may reveal problematic reasoning. But scrutinizing highlights over many data instances is tedious and often infeasible. Furthermore, analyzing examples in isolation does not reveal general patterns in the data or in the model's behavior. In this paper we aim to address these issues and go from understanding single examples to understanding entire datasets and models. The methodology we propose is based on aggregated salience maps. Using this methodology we address multiple distinct but common model developer needs by showing how problematic data and model behavior can be identified -- a necessary first step for improving the model.

This paper presents SimCSE, a simple contrastive learning framework that greatly advances state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrastive objective, with only standard dropout used as noise. This simple method works surprisingly well, performing on par with previous supervised counterparts. We find that dropout acts as minimal data augmentation, and removing it leads to a representation collapse. Then, we propose a supervised approach, which incorporates annotated pairs from natural language inference datasets into our contrastive learning framework by using "entailment" pairs as positives and "contradiction" pairs as hard negatives. We evaluate SimCSE on standard semantic textual similarity (STS) tasks, and our unsupervised and supervised models using BERT base achieve an average of 76.3% and 81.6% Spearman's correlation respectively, a 4.2% and 2.2% improvement compared to the previous best results. We also show-both theoretically and empirically-that the contrastive learning objective regularizes pre-trained embeddings' anisotropic space to be more uniform, and it better aligns positive pairs when supervised signals are available. 1 2 We randomly sample 10 6 sentences from English Wikipedia and fine-tune BERTbase with learning rate = 3e-5, N = 64. In all our experiments, no STS training sets are used.

The widely studied task of Natural Language Inference (NLI) requires a system to recognize whether one piece of text is textually entailed by another, i.e. whether the entirety of its meaning can be inferred from the other. In current NLI datasets and models, textual entailment relations are typically defined on the sentence- or paragraph-level. However, even a simple sentence often contains multiple propositions, i.e. distinct units of meaning conveyed by the sentence. As these propositions can carry different truth values in the context of a given premise, we argue for the need to recognize the textual entailment relation of each proposition in a sentence individually. We propose PropSegmEnt, a corpus of over 35K propositions annotated by expert human raters. Our dataset structure resembles the tasks of (1) segmenting sentences within a document to the set of propositions, and (2) classifying the entailment relation of each proposition with respect to a different yet topically-aligned document, i.e. documents describing the same event or entity. We establish strong baselines for the segmentation and entailment tasks. Through case studies on summary hallucination detection and document-level NLI, we demonstrate that our conceptual framework is potentially useful for understanding and explaining the compositionality of NLI labels.

对自然语言处理资源中的偏置模式的提高意识，如BERT，具有许多度量来量化“偏见”和“公平”。但是，如果没有完全不可能，请比较不同指标的结果和评估这些度量的作品仍然困难。我们调查了对预用语言模型的公平度量标准的现有文献，并通过实验评估兼容性，包括语言模型中的偏差，如在其下游任务中。我们通过传统文献调查和相关分析的混合来实现这一目标，以及运行实证评估。我们发现许多指标不兼容，高度依赖于（i）模板，（ii）属性和目标种子和（iii）选择嵌入式。这些结果表明，公平或偏见评估对情境化语言模型仍然具有挑战性，如果不是至少高度主观。为了提高未来的比较和公平评估，我们建议避免嵌入基于的指标并专注于下游任务中的公平评估。

语言模型中的上下文化单词嵌入已为NLP提供了很大的进步。直观地，句子信息集成到单词的表示中，这可以帮助模型多义。但是，上下文灵敏度也导致表示形式的差异，这可能会破坏同义词的语义一致性。我们量化了典型的预训练模型中每个单词sense的上下文嵌入的程度各不相同。结果表明，在上下文中，上下文化的嵌入可以高度一致。此外，词性，单词感官的数量和句子长度对感官表示的差异有影响。有趣的是，我们发现单词表示是偏见的，在不同上下文中的第一个单词往往更相似。我们分析了这种现象，还提出了一种简单的方法来减轻基于距离的单词sense剥夺歧义设置的偏见。

自然语言推论（NLI）是自然语言处理中的热门话题研究，句子之间的矛盾检测是NLI的特殊情况。这被认为是一项困难的NLP任务，当在许多NLP应用程序中添加为组件时，其影响很大，例如问答系统，文本摘要。阿拉伯语是由于其丰富的词汇，语义歧义而检测矛盾的最具挑战性的低资源语言之一。我们创建了一个超过12K句子的数据集并命名为Arnli，这将是公开可用的。此外，我们采用了一种新的模型，该模型受到斯坦福大学矛盾检测的启发，提出了有关英语的解决方案。我们提出了一种方法，以使用矛盾向量与语言模型向量作为机器学习模型的输入来检测阿拉伯语对句子之间的矛盾。我们分析了不同传统的机器学习分类器的结果，并比较了他们在创建的数据集（Arnli）和Pheme，病态的英语数据集的自动翻译上进行了比较。使用随机森林分类器，精度为99％，60％和75％的Pheme，Sick和Arnli的最佳结果。

Contrastive learning has become a new paradigm for unsupervised sentence embeddings. Previous studies focus on instance-wise contrastive learning, attempting to construct positive pairs with textual data augmentation. In this paper, we propose a novel Contrastive learning method with Prompt-derived Virtual semantic Prototypes (ConPVP). Specifically, with the help of prompts, we construct virtual semantic prototypes to each instance, and derive negative prototypes by using the negative form of the prompts. Using a prototypical contrastive loss, we enforce the anchor sentence embedding to be close to its corresponding semantic prototypes, and far apart from the negative prototypes as well as the prototypes of other sentences. Extensive experimental results on semantic textual similarity, transfer, and clustering tasks demonstrate the effectiveness of our proposed model compared to strong baselines. Code is available at https://github.com/lemon0830/promptCSE.

大型预训练的语言模型通常受到大量互联网数据的培训，其中一些可能包含有毒或滥用语言。因此，语言模型编码有毒信息，这使得这些语言模型有限的真实应用。目前的方法旨在防止出现有毒功能出现生成的文本。我们假设在预训练的语言模型的潜在空间中存在低维毒子空间，其存在表明有毒特征遵循一些底层图案，因此可拆卸。为了构建这种有毒的子空间，我们提出了一种方法来概括潜在空间中的毒性方向。我们还提供了一种使用基于上下文的Word Masking系统构造并行数据集的方法。通过我们的实验，我们表明，当从一组句子表现中删除有毒的子空间时，结果几乎没有毒性表现。我们凭经验证明了使用我们的方法发现的子空间推广到多个毒性Corpora，表明存在低维毒子空间。