Interpretable entity representations (IERs) are sparse embeddings that are "human-readable" in that dimensions correspond to fine-grained entity types and values are predicted probabilities that a given entity is of the corresponding type. These methods perform well in zero-shot and low supervision settings. Compared to standard dense neural embeddings, such interpretable representations may permit analysis and debugging. However, while fine-tuning sparse, interpretable representations improves accuracy on downstream tasks, it destroys the semantics of the dimensions which were enforced in pre-training. Can we maintain the interpretable semantics afforded by IERs while improving predictive performance on downstream tasks? Toward this end, we propose Intermediate enTity-based Sparse Interpretable Representation Learning (ItsIRL). ItsIRL realizes improved performance over prior IERs on biomedical tasks, while maintaining "interpretability" generally and their ability to support model debugging specifically. The latter is enabled in part by the ability to perform "counterfactual" fine-grained entity type manipulation, which we explore in this work. Finally, we propose a method to construct entity type based class prototypes for revealing global semantic properties of classes learned by our model.

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a;Radford et al., 2018), BERT is designed to pretrain deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be finetuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial taskspecific architecture modifications.BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

With the success of the prompt-tuning paradigm in Natural Language Processing (NLP), various prompt templates have been proposed to further stimulate specific knowledge for serving downstream tasks, e.g., machine translation, text generation, relation extraction, and so on. Existing prompt templates are mainly shared among all training samples with the information of task description. However, training samples are quite diverse. The sharing task description is unable to stimulate the unique task-related information in each training sample, especially for tasks with the finite-label space. To exploit the unique task-related information, we imitate the human decision process which aims to find the contrastive attributes between the objective factual and their potential counterfactuals. Thus, we propose the \textbf{C}ounterfactual \textbf{C}ontrastive \textbf{Prompt}-Tuning (CCPrompt) approach for many-class classification, e.g., relation classification, topic classification, and entity typing. Compared with simple classification tasks, these tasks have more complex finite-label spaces and are more rigorous for prompts. First of all, we prune the finite label space to construct fact-counterfactual pairs. Then, we exploit the contrastive attributes by projecting training instances onto every fact-counterfactual pair. We further set up global prototypes corresponding with all contrastive attributes for selecting valid contrastive attributes as additional tokens in the prompt template. Finally, a simple Siamese representation learning is employed to enhance the robustness of the model. We conduct experiments on relation classification, topic classification, and entity typing tasks in both fully supervised setting and few-shot setting. The results indicate that our model outperforms former baselines.

Metric-based meta-learning is one of the de facto standards in few-shot learning. It composes of representation learning and metrics calculation designs. Previous works construct class representations in different ways, varying from mean output embedding to covariance and distributions. However, using embeddings in space lacks expressivity and cannot capture class information robustly, while statistical complex modeling poses difficulty to metric designs. In this work, we use tensor fields (``areas'') to model classes from the geometrical perspective for few-shot learning. We present a simple and effective method, dubbed hypersphere prototypes (HyperProto), where class information is represented by hyperspheres with dynamic sizes with two sets of learnable parameters: the hypersphere's center and the radius. Extending from points to areas, hyperspheres are much more expressive than embeddings. Moreover, it is more convenient to perform metric-based classification with hypersphere prototypes than statistical modeling, as we only need to calculate the distance from a data point to the surface of the hypersphere. Following this idea, we also develop two variants of prototypes under other measurements. Extensive experiments and analysis on few-shot learning tasks across NLP and CV and comparison with 20+ competitive baselines demonstrate the effectiveness of our approach.

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.

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.

We present Pre-trained Machine Reader (PMR), a novel method to retrofit Pre-trained Language Models (PLMs) into Machine Reading Comprehension (MRC) models without acquiring labeled data. PMR is capable of resolving the discrepancy between model pre-training and downstream fine-tuning of existing PLMs, and provides a unified solver for tackling various extraction tasks. To achieve this, we construct a large volume of general-purpose and high-quality MRC-style training data with the help of Wikipedia hyperlinks and design a Wiki Anchor Extraction task to guide the MRC-style pre-training process. Although conceptually simple, PMR is particularly effective in solving extraction tasks including Extractive Question Answering and Named Entity Recognition, where it shows tremendous improvements over previous approaches especially under low-resource settings. Moreover, viewing sequence classification task as a special case of extraction task in our MRC formulation, PMR is even capable to extract high-quality rationales to explain the classification process, providing more explainability of the predictions.

我们介绍了精致的，这是一种有效的端到端实体链接模型，该模型使用精细的实体类型和实体描述来执行链接。该模型执行提及的检测，细粒实体键入以及单个向前传球中文档中所有提及的实体歧义，使其比现有方法快60倍以上。精制还超过了标准实体链接数据集的最先进性能，平均比3.7 F1。该模型能够将其推广到大规模的知识库，例如Wikidata（其实体是Wikipedia的15倍）和零拍的实体链接。速度，准确性和规模的结合使精制成为从网络规模数据集中提取实体的有效且具有成本效益的系统，该数据集已成功部署该模型。我们的代码和预培训模型可在https://github.com/alexa/refined上找到

专门的基于变形金刚的模型（例如生物Biobert和Biomegatron）适用于基于公共可用的生物医学语料库的生物医学领域。因此，它们有可能编码大规模的生物学知识。我们研究了这些模型中生物学知识的编码和表示，及其支持癌症精度医学推断的潜在实用性 - 即，对基因组改变的临床意义的解释。我们比较不同变压器基线的性能；我们使用探测来确定针对不同实体的编码的一致性；我们使用聚类方法来比较和对比基因，变异，药物和疾病的嵌入的内部特性。我们表明，这些模型确实确实编码了生物学知识，尽管其中一些模型在针对特定任务的微调中丢失了。最后，我们分析了模型在数据集中的偏见和失衡方面的行为。

我们为指定实体识别（NER）提出了一个有效的双重编码框架，该框架将对比度学习用于映射候选文本跨度，并将实体类型映射到同一矢量表示空间中。先前的工作主要将NER作为序列标记或跨度分类。相反，我们将NER视为一个度量学习问题，它最大程度地提高了实体提及的向量表示之间的相似性及其类型。这使得易于处理嵌套和平坦的ner，并且可以更好地利用嘈杂的自我诉讼信号。 NER对本双重编码器制定的主要挑战在于将非实体跨度与实体提及分开。我们没有明确标记所有非实体跨度为外部（O）与大多数先前方法相同的类别（O），而是引入了一种新型的动态阈值损失，这与标准的对比度损失一起学习。实验表明，我们的方法在受到监督和远处有监督的设置中的表现良好（例如，Genia，NCBI，BC5CDR，JNLPBA）。

We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Our word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pretrained on a large text corpus. We show that these representations can be easily added to existing models and significantly improve the state of the art across six challenging NLP problems, including question answering, textual entailment and sentiment analysis. We also present an analysis showing that exposing the deep internals of the pre-trained network is crucial, allowing downstream models to mix different types of semi-supervision signals.

关系提取（RE）是自然语言处理的基本任务。RE试图通过识别文本中的实体对之间的关系信息来将原始的，非结构化的文本转变为结构化知识。RE有许多用途，例如知识图完成，文本摘要，提问和搜索查询。RE方法的历史可以分为四个阶段：基于模式的RE，基于统计的RE，基于神经的RE和大型语言模型的RE。这项调查始于对RE的早期阶段的一些示例性作品的概述，突出了局限性和缺点，以使进度相关。接下来，我们回顾流行的基准测试，并严格检查用于评估RE性能的指标。然后，我们讨论遥远的监督，这是塑造现代RE方法发展的范式。最后，我们回顾了重点是降级和培训方法的最新工作。

知识密集型语言任务（苏格兰信）通常需要大量信息来提供正确的答案。解决此问题的一种流行范式是将搜索系统与机器读取器相结合，前者检索支持证据，后者检查它们以产生答案。最近，读者组成部分在大规模预培养的生成模型的帮助下见证了重大进展。同时，搜索组件中的大多数现有解决方案都依赖于传统的``索引 - retrieve-then-Rank''管道，该管道遭受了巨大的内存足迹和端到端优化的困难。受到最新构建基于模型的IR模型的努力的启发，我们建议用新颖的单步生成模型替换传统的多步搜索管道，该模型可以极大地简化搜索过程并以端到端的方式进行优化。我们表明，可以通过一组经过适当设计的预训练任务来学习强大的生成检索模型，并被采用以通过进一步的微调来改善各种下游苏格兰短裙任务。我们将预训练的生成检索模型命名为Copusbrain，因为有关该语料库的所有信息均以其参数进行编码，而无需构造其他索引。经验结果表明，在苏格兰语基准上的检索任务并建立了新的最新性能，Copusbrain可以极大地超过强大的基准。我们还表明，在零农源和低资源设置下，科体班运行良好。

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.

自我监督的视觉表示学习最近引起了重大的研究兴趣。虽然一种评估自我监督表示的常见方法是通过转移到各种下游任务，但我们研究了衡量其可解释性的问题，即了解原始表示中编码的语义。我们将后者提出为估计表示和手动标记概念空间之间的相互信息。为了量化这一点，我们介绍了一个解码瓶颈：必须通过简单的预测变量捕获信息，将概念映射到表示空间中的簇。我们称之为反向线性探测的方法为表示表示的语义敏感。该措施还能够检测出表示何时包含概念的组合（例如“红色苹果”），而不仅仅是单个属性（独立的“红色”和“苹果”）。最后，我们建议使用监督分类器自动标记大型数据集，以丰富用于探测的概念的空间。我们使用我们的方法来评估大量的自我监督表示形式，通过解释性对它们进行排名，并通过线性探针与标准评估相比出现的差异，并讨论了一些定性的见解。代码为：{\ Scriptsize {\ url {https://github.com/iro-cp/ssl-qrp}}}}}。

The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a more practical scenario, where we use smaller language models for which fine-tuning is computationally efficient. We present LM-BFF-better few-shot fine-tuning of language models 1 -a suite of simple and complementary techniques for finetuning language models on a small number of annotated examples. Our approach includes (1) prompt-based fine-tuning together with a novel pipeline for automating prompt generation; and (2) a refined strategy for dynamically and selectively incorporating demonstrations into each context. Finally, we present a systematic evaluation for analyzing few-shot performance on a range of NLP tasks, including classification and regression. Our experiments demonstrate that our methods combine to dramatically outperform standard fine-tuning procedures in this low resource setting, achieving up to 30% absolute improvement, and 11% on average across all tasks. Our approach makes minimal assumptions on task resources and domain expertise, and hence constitutes a strong task-agnostic method for few-shot learning. 2 * The first two authors contributed equally. 1 Alternatively, language models' best friends forever. 2 Our implementation is publicly available at https:// github.com/princeton-nlp/LM-BFF.

几个名称的实体识别（NER）使我们能够使用很少的标记示例为新域构建一个NER系统。但是，该任务的现有原型网络具有大致估计的标签依赖性和紧密分布的原型，因此经常导致错误分类。为了解决上述问题，我们提出了EP-NET，这是一个实体级原型网络，通过分散分布的原型增强。EP-NET构建实体级原型，并认为文本跨度为候选实体，因此它不再需要标签依赖性。此外，EP-NET从头开始训练原型，以分散分配它们，并使用空间投影将跨度与嵌入空间中的原型对齐。两项评估任务和少量网络设置的实验结果表明，EP-NET在整体性能方面始终优于先前的强大模型。广泛的分析进一步验证了EP-NET的有效性。

零拍的学习依赖于语义类表示，例如手工设计的属性或学习的嵌入方式来预测类，而无需任何标记的示例。我们建议通过将节点从矢量空间中的常识知识图中嵌入节点来学习班级表示。常识知识图是未开发的明确高级知识的来源，几乎不需要人类的努力才能应用于一系列任务。为了捕获图中的知识，我们引入了ZSL-KG，这是一种具有新型变压器图卷积网络（TRGCN）的通用框架，用于生成类表示。我们提出的TRGCN体系结构计算节点社区的非线性组合。我们的结果表明，ZSL-KG在语言和视觉中的六个零弹药基准数据集中有五个基于WordNet的方法改进了基于WordNet的方法。

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.

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。