Text-to-text generation models have increasingly become the go-to solution for a wide variety of sequence labeling tasks (e.g., entity extraction and dialog slot filling). While most research has focused on the labeling accuracy, a key aspect -- of vital practical importance -- has slipped through the cracks: understanding model confidence. More specifically, we lack a principled understanding of how to reliably gauge the confidence of a model in its predictions for each labeled span. This paper aims to provide some empirical insights on estimating model confidence for generative sequence labeling. Most notably, we find that simply using the decoder's output probabilities is not the best in realizing well-calibrated confidence estimates. As verified over six public datasets of different tasks, we show that our proposed approach -- which leverages statistics from top-$k$ predictions by a beam search -- significantly reduces calibration errors of the predictions of a generative sequence labeling model.

顺序标记是一项基本的NLP任务，构成了许多应用程序的骨干。对SEQ2SEQ模型的监督学习（如T5）在这些问题上取得了巨大的成功。但是，这些模型的培训目标与我们在实际应用中关心的指标和Desiderata之间存在显着脱节。例如，实用的序列标记应用程序可能需要优化某些Precision-Recall折衷（TOP-K预测），这与最大化金标记序列的可能性的标准目标完全不同。因此，为了弥合这一差距，我们提出了Groot，这是一个简单而有效的框架，用于生成文本序列的奖励优化。 Groot通过训练生成的顺序标记模型来工作，以将解码器输出分布与（Black-Box）奖励函数的输出分布相匹配。使用迭代培训制度，我们首先生成预测候选者，然后纠正其中的错误，最后对比这些候选者（基于其奖励价值）。正如通过四个公共基准测试的广泛实验所证明的那样，Groot显着改善了所有奖励指标。此外，Groot还导致了整体解码器分布的改善，这是由顶级$ K $候选者的质量提高所证明的。

In the absence of readily available labeled data for a given task and language, annotation projection has been proposed as one of the possible strategies to automatically generate annotated data which may then be used to train supervised systems. Annotation projection has often been formulated as the task of projecting, on parallel corpora, some labels from a source into a target language. In this paper we present T-Projection, a new approach for annotation projection that leverages large pretrained text2text language models and state-of-the-art machine translation technology. T-Projection decomposes the label projection task into two subtasks: (i) The candidate generation step, in which a set of projection candidates using a multilingual T5 model is generated and, (ii) the candidate selection step, in which the candidates are ranked based on translation probabilities. We evaluate our method in three downstream tasks and five different languages. Our results show that T-projection improves the average F1 score of previous methods by more than 8 points.

Task-oriented semantic parsing is increasingly being used in user-facing applications, making measuring the calibration of parsing models especially important. We examine the calibration characteristics of six models across three model families on two common English semantic parsing datasets, finding that many models are reasonably well-calibrated and that there is a trade-off between calibration and performance. Based on confidence scores across three models, we propose and release new challenge splits of the two datasets we examine. We then illustrate the ways a calibrated model can be useful in balancing common trade-offs in task-oriented parsing. In a simulated annotator-in-the-loop experiment, we show that using model confidence allows us to improve the accuracy on validation programs by 9.6% (absolute) with annotator interactions on only 2.2% of tokens. Using sequence-level confidence scores, we then examine how we can optimize trade-off between a parser's usability and safety. We show that confidence-based thresholding can reduce the number of incorrect low-confidence programs executed by 76%; however, this comes at a cost to usability. We propose the DidYouMean system which balances usability and safety. We conclude by calling for calibration to be included in the evaluation of semantic parsing systems, and release a library for computing calibration metrics.

注释数据是用于培训和评估机器学习模型的自然语言处理中的重要成分。因此，注释具有高质量是非常理想的。但是，最近的工作表明，几个流行的数据集包含令人惊讶的注释错误或不一致之处。为了减轻此问题，多年来已经设计了许多注释错误检测方法。尽管研究人员表明他们的方法在新介绍的数据集上效果很好，但他们很少将其方法与以前的工作或同一数据集进行比较。这引起了人们对方法的一般表现的强烈关注，并且使他们的优势和劣势很难解决。因此，我们重新实现18种检测潜在注释错误的方法，并在9个英语数据集上对其进行评估，以进行文本分类以及令牌和跨度标签。此外，我们定义了统一的评估设置，包括注释错误检测任务，评估协议和一般最佳实践的新形式化。为了促进未来的研究和可重复性，我们将数据集和实施释放到易于使用和开源软件包中。

我们提出了一个新的框架，在增强的自然语言（TANL）之间的翻译，解决了许多结构化预测语言任务，包括联合实体和关系提取，嵌套命名实体识别，关系分类，语义角色标记，事件提取，COREREFED分辨率和对话状态追踪。通过培训特定于特定于任务的鉴别分类器来说，我们将其作为一种在增强的自然语言之间的翻译任务，而不是通过培训问题，而不是解决问题，而是可以轻松提取任务相关信息。我们的方法可以匹配或优于所有任务的特定于任务特定模型，特别是在联合实体和关系提取（Conll04，Ade，NYT和ACE2005数据集）上实现了新的最先进的结果，与关系分类（偶尔和默示）和语义角色标签（Conll-2005和Conll-2012）。我们在使用相同的架构和超参数的同时为所有任务使用相同的架构和超级参数，甚至在培训单个模型时同时解决所有任务（多任务学习）。最后，我们表明，由于更好地利用标签语义，我们的框架也可以显着提高低资源制度的性能。

Recent advances in large-scale pre-training provide large models with the potential to learn knowledge from the raw text. It is thus natural to ask whether it is possible to leverage these large models as knowledge bases for downstream tasks. In this work, we answer the aforementioned question in unsupervised knowledge-grounded conversation. We explore various methods that best elicit knowledge from large models. Our human study indicates that, though hallucinations exist, large models post the unique advantage of being able to output common sense and summarize facts that cannot be directly retrieved from the search engine. To better exploit such generated knowledge in dialogue generation, we treat the generated knowledge as a noisy knowledge source and propose the posterior-based reweighing as well as the noisy training strategy. Empirical results on two benchmarks show advantages over the state-of-the-art methods.

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）。

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.

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。

Triplet extraction aims to extract entities and their corresponding relations in unstructured text. Most existing methods train an extraction model on high-quality training data, and hence are incapable of extracting relations that were not observed during training. Generalizing the model to unseen relations typically requires fine-tuning on synthetic training data which is often noisy and unreliable. In this paper, we argue that reducing triplet extraction to a template filling task over a pre-trained language model can equip the model with zero-shot learning capabilities and enable it to leverage the implicit knowledge in the language model. Embodying these ideas, we propose a novel framework, ZETT (ZEro-shot Triplet extraction by Template infilling), that is based on end-to-end generative transformers. Our experiments show that without any data augmentation or pipeline systems, ZETT can outperform previous state-of-the-art models with 25% less parameters. We further show that ZETT is more robust in detecting entities and can be incorporated with automatically generated templates for relations.

We study the performance of monolingual and multilingual language models on the task of question-answering (QA) on three diverse languages: English, Finnish and Japanese. We develop models for the tasks of (1) determining if a question is answerable given the context and (2) identifying the answer texts within the context using IOB tagging. Furthermore, we attempt to evaluate the effectiveness of a pre-trained multilingual encoder (Multilingual BERT) on cross-language zero-shot learning for both the answerability and IOB sequence classifiers.

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.

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.

最先进的抽象摘要系统经常生成\ emph {幻觉};即，不直接从源文本中推断的内容。尽管被认为是不正确的，我们发现非常令人难潮的内容是事实，即与世界知识一致。这些事实幻觉通过提供有用的背景信息，可以在摘要中受益。在这项工作中，我们提出了一种新的检测方法，将事实与实体的非事实幻觉分开。我们的方法分别使用实体的先前和后验概率，分别是预训练和芬特的屏蔽语言模型。经验结果表明，我们的方法在精度和F1分数方面大大优于两种基线％，与人类判断强烈相关。百分比对事实分类任务。此外，我们显示我们的探测器，当用作离线增强学习（RL）算法中的奖励信号时，显着提高了摘要的事实性，同时保持抽象水平。

我们介绍了AARGH，这是一个面向任务的对话框系统，该系统结合了单个模型中的检索和生成方法，旨在改善对话框管理和输出的词汇多样性。该模型采用了一种新的响应选择方法，该方法基于动作感知训练目标和简化的单编码检索架构，该方法使我们能够构建端到端检索增强生成模型，在该模型中，检索和生成共享大多数参数。在Multiwoz数据集上，我们表明我们的方法与最先进的基线相比，在维持或改善状态跟踪和上下文响应生成性能的同时，产生了更多的输出。

首字母缩略词提取旨在从文件中找到首字母缩略词（即，短文）及其含义（即，长形式），这对于科学文件理解（SDU @ Aaai-22）任务很重要。以前的作品致力于将此任务建模为段落级序列标记问题。但是，它缺乏有效利用外部知识，尤其是当数据集处于低资源设置时。最近，具有庞大培训的语言模型的基于及时的方法可以显着提高低资源下游任务的性能。在本文中，我们提出了一种用于缩写式提取任务的基于行的序列生成（PSG）方法。具体来说，我们设计一个模板，用于提示带有自动回归的提取的缩写文本。位置提取算法旨在提取所生成答案的位置。在低资源设置中越南语和波斯语的缩写提取的结果表明，所提出的方法优于所有其他竞争全能（SOTA）方法。

对于指定的实体识别（NER），基于序列标签和基于跨度的范例大不相同。先前的研究表明，这两个范式具有明显的互补优势，但是据我们所知，很少有模型试图在单个NER模型中利用这些优势。在我们以前的工作中，我们提出了一种称为捆绑学习（BL）的范式来解决上述问题。 BL范式将两个NER范式捆绑在一起，从而使NER模型通过加权总结每个范式的训练损失来共同调整其参数。但是，三个关键问题仍未解决：BL何时起作用？ BL为什么工作？ BL可以增强现有的最新（SOTA）NER模型吗？为了解决前两个问题，我们实施了三个NER模型，涉及一个基于序列标签的模型-Seqner，Seqner，一个基于跨度的NER模型 - 机器人，以及将Seqner和Spanner捆绑在一起的BL-NER。我们根据来自五个域的11个NER数据集的实验结果得出两个关于这两个问题的结论。然后，我们将BL应用于现有的五个SOTA NER模型，以研究第三期，包括三个基于序列标签的模型和两个基于SPAN的模型。实验结果表明，BL始终提高其性能，表明可以通过将BL纳入当前的SOTA系统来构建新的SOTA NER系统。此外，我们发现BL降低了实体边界和类型预测错误。此外，我们比较了两种常用的标签标签方法以及三种类型的跨度语义表示。

We explore the use of large language models (LLMs) for zero-shot semantic parsing. Semantic parsing involves mapping natural language utterances to task-specific meaning representations. Language models are generally trained on the publicly available text and code and cannot be expected to directly generalize to domain-specific parsing tasks in a zero-shot setting. In this work, we propose ZEROTOP, a zero-shot task-oriented parsing method that decomposes a semantic parsing problem into a set of abstractive and extractive question-answering (QA) problems, enabling us to leverage the ability of LLMs to zero-shot answer reading comprehension questions. For each utterance, we prompt the LLM with questions corresponding to its top-level intent and a set of slots and use the LLM generations to construct the target meaning representation. We observe that current LLMs fail to detect unanswerable questions; and as a result, cannot handle questions corresponding to missing slots. To address this problem, we fine-tune a language model on public QA datasets using synthetic negative samples. Experimental results show that our QA-based decomposition paired with the fine-tuned LLM can correctly parse ~16% of utterances in the MTOP dataset without requiring any annotated data.

谈话问题应答需要能够正确解释问题。然而，由于在日常谈话中难以理解共同参考和省略号的难度，目前的模型仍然不令人满意。尽管生成方法取得了显着的进展，但它们仍然被语义不完整陷入困境。本文提出了一种基于动作的方法来恢复问题的完整表达。具体地，我们首先在将相应的动作分配给每个候选跨度的同时定位问题中的共同引用或省略号的位置。然后，我们寻找与对话环境中的候选线索相关的匹配短语。最后，根据预测的操作，我们决定是否用匹配的信息替换共同参考或补充省略号。我们展示了我们对英语和中文发言权重写任务的方法的有效性，在RESTORATION-200K数据集中分别在3.9 \％和Rouge-L中提高了最先进的EM（完全匹配）。