自然语言处理研究人员已经确定了对生成任务的评估方法的局限性，具有新的问题，提出了自动指标和人群判断的有效性。同时，改善生成模型的努力倾向于专注于简单的n-gram重叠度量（例如，Bleu，Rouge）。我们认为，对模型和指标的新进展应该每个人都更直接受益并告知另一个。因此，我们提出了排行榜，竞争排行榜（广告牌）的概括，同时跟踪语言生成任务和指标的进展。与通过预定度量分类提交系统的传统的单向排行榜不同，广告牌可接受发电机和评估度量作为竞争条目。广告牌会自动创建一个基于跨发电机的全局分析选择和线性地组合一些指标的集合度量。此外，指标基于与人类判断的相关性进行排序。我们释放了用于机器翻译，摘要和图像标题的四个广告牌。我们展示了一些多样化度量的线性集合有时会在隔离中显着优于现有的度量。我们的混合效果模型分析表明，大多数自动度量，尤其是基于参考的机器，对人类发电的重估，展示了更新度量的重要性，将来变得更强大（也许与人类更相似）。

我们建立了一种基于规校的图像标题模型的人类评估协议。我们的得分标准及其定义是基于MSCOCO数据集上的机器和人类生成的标题仔细开发。每个字幕沿着权衡（精确和召回）中的两个主要尺寸以及测量文本质量的其他方面（流利，简洁，包容性语言）。我们的评估表明了当前评估实践的几个关键问题。人生成的标题显示出比机器生成的字块的质量大得多，特别是在突出信息的覆盖范围内（即，召回），而所有自动度量都可以说相反。我们基于规度的标准结果表明，曲线芯片，最近使用图像特征的度量标准，与人类判断更好地相关，因为它对召回更敏感。我们希望这项工作将推动更透明的图像标题和自动指标的评估协议。

We propose BERTSCORE, an automatic evaluation metric for text generation. Analogously to common metrics, BERTSCORE computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However, instead of exact matches, we compute token similarity using contextual embeddings. We evaluate using the outputs of 363 machine translation and image captioning systems. BERTSCORE correlates better with human judgments and provides stronger model selection performance than existing metrics. Finally, we use an adversarial paraphrase detection task to show that BERTSCORE is more robust to challenging examples when compared to existing metrics.

Human evaluation is the foundation upon which the evaluation of both summarization systems and automatic metrics rests. However, existing human evaluation protocols and benchmarks for summarization either exhibit low inter-annotator agreement or lack the scale needed to draw statistically significant conclusions, and an in-depth analysis of human evaluation is lacking. In this work, we address the shortcomings of existing summarization evaluation along the following axes: 1) We propose a modified summarization salience protocol, Atomic Content Units (ACUs), which relies on fine-grained semantic units and allows for high inter-annotator agreement. 2) We curate the Robust Summarization Evaluation (RoSE) benchmark, a large human evaluation dataset consisting of over 22k summary-level annotations over state-of-the-art systems on three datasets. 3) We compare our ACU protocol with three other human evaluation protocols, underscoring potential confounding factors in evaluation setups. 4) We evaluate existing automatic metrics using the collected human annotations across evaluation protocols and demonstrate how our benchmark leads to more statistically stable and significant results. Furthermore, our findings have important implications for evaluating large language models (LLMs), as we show that LLMs adjusted by human feedback (e.g., GPT-3.5) may overfit unconstrained human evaluation, which is affected by the annotators' prior, input-agnostic preferences, calling for more robust, targeted evaluation methods.

质量摘要数据集的创建是一种昂贵，耗时的努力，需要通过训练有素的人类和机器的摘要生产和评估。如果这种努力用一种语言制作，则能够在不重复人类注释的情况下用其他语言使用它是有益的。要调查我们可以信任此类数据集的机器翻译多少，我们将英文数据集汇总到七种语言，并在自动评估措施中比较性能。我们将等同性测试探讨为适当的统计范式，用于评估摘要人类自动评分之间的相关性。虽然我们发现类似于源类似语言的数据集重用潜力，但在横跨翻译中找不到大多数摘要评估方法。

Text generation has made significant advances in the last few years. Yet, evaluation metrics have lagged behind, as the most popular choices (e.g., BLEU and ROUGE) may correlate poorly with human judgments. We propose BLEURT, a learned evaluation metric based on BERT that can model human judgments with a few thousand possibly biased training examples. A key aspect of our approach is a novel pre-training scheme that uses millions of synthetic examples to help the model generalize. BLEURT provides state-ofthe-art results on the last three years of the WMT Metrics shared task and the WebNLG Competition dataset. In contrast to a vanilla BERT-based approach, it yields superior results even when the training data is scarce and out-of-distribution.

文本生成的广泛使用的评估指标要么与更长的文本效果不错，要么无法评估文本质量的所有方面。在本文中，我们引入了一个名为SMART的新指标，以减轻此类限制。具体而言，我们将句子视为匹配的基本单位，而不是代币，并使用句子匹配函数来匹配匹配候选和参考句子。还将候选句子与源文件中的句子进行了比较，以允许接地（例如，事实）评估。我们的结果表明，我们提出的指标与基于模型的匹配函数的系统级相关性优于萨姆瓦尔摘要元评估数据集上的所有竞争指标指标。后者不使用任何神经模型，这在模型开发阶段很有用，在这些阶段，资源可以受到限制且需要快速评估。最后，我们还进行了广泛的分析，表明我们提出的指标与较长的摘要很好地运行，并且对特定模型的偏见较小。

In this work, we explore a useful but often neglected methodology for robustness analysis of text generation evaluation metrics: stress tests with synthetic data. Basically, we design and synthesize a wide range of potential errors and check whether they result in a commensurate drop in the metric scores. We examine a range of recently proposed evaluation metrics based on pretrained language models, for the tasks of open-ended generation, translation, and summarization. Our experiments reveal interesting insensitivities, biases, or even loopholes in existing metrics. For example, we find that BERTScore ignores truncation errors in summarization, and MAUVE (built on top of GPT-2) is insensitive to errors at the beginning of generations. Further, we investigate the reasons behind these blind spots and suggest practical workarounds for a more reliable evaluation of text generation.

图像字幕是当前的研究任务，用于使用场景中的对象及其关系来描述图像内容。为了应对这项任务，使用了两个重要的研究领域，人为的视觉和自然语言处理。在图像字幕中，就像在任何计算智能任务中一样，性能指标对于知道方法的性能（或坏）至关重要。近年来，已经观察到，基于n-gram的经典指标不足以捕获语义和关键含义来描述图像中的内容。为了衡量或不进行最新指标的集合，在本手稿中，我们对使用众所周知的COCO数据集进行了对几种图像字幕指标的评估以及它们之间的比较。为此，我们设计了两种情况。 1）一组人工构建字幕，以及2）比较某些最先进的图像字幕方法的比较。我们试图回答问题：当前的指标是否有助于制作高质量的标题？实际指标如何相互比较？指标真正测量什么？

近年来，研究人员创建并引入了大量各种代码生成模型。由于对每个新模型版本的人类评估都是不可行的，因此社区采用了自动评估指标，例如BLEU来近似人类判断的结果。这些指标源自机器翻译域，目前尚不清楚它们是否适用于代码生成任务，以及他们与人类对此任务的评估有多一致。还有两个指标，即Codebleu和Ruby，它们是为了估计代码的相似性并考虑了代码属性的。但是，对于这些指标，几乎没有关于他们与人类评估一致的研究。尽管如此，公制得分的最小差异仍用于声称某些代码生成模型的优越性。在本文中，我们介绍了一项有关六个指标的适用性的研究-Bleu，Rouge-L，Meteor，Chrf，Codebleu，Ruby-用于评估代码生成模型。我们对两个不同的代码生成数据集进行了一项研究，并使用人类注释来评估这些数据集上运行的所有模型的质量。结果表明，对于Python单线的Conala数据集，如果模型得分的差异小于5分，则没有一个指标可以正确模拟人类判断，而$ 95 \％$确定性，则使用$> 95 \％$确定性。对于由特定结构类别组成的炉石传说数据集，至少2分的模型得分差异足以声称一种模型比另一个模型的优越性。使用我们的发现，我们得出了有关使用指标来估计代码生成任务的模型性能的几项建议。

The publication rates are skyrocketing across many fields of science, and it is difficult to stay up to date with the latest research. This makes automatically summarizing the latest findings and helping scholars to synthesize related work in a given area an attractive research objective. In this paper we study the problem of citation text generation, where given a set of cited papers and citing context the model should generate a citation text. While citation text generation has been tackled in prior work, existing studies use different datasets and task definitions, which makes it hard to study citation text generation systematically. To address this, we propose CiteBench: a benchmark for citation text generation that unifies the previous datasets and enables standardized evaluation of citation text generation models across task settings and domains. Using the new benchmark, we investigate the performance of multiple strong baselines, test their transferability between the datasets, and deliver new insights into task definition and evaluation to guide the future research in citation text generation. We make CiteBench publicly available at https://github.com/UKPLab/citebench.

最近提出的基于BERT的评估指标在标准评估基准方面表现良好，但容易受到对抗性攻击的影响，例如与事实错误有关。我们认为这（部分原因）是因为它们是语义相似性的模型。相反，我们根据自然语言推断（NLI）制定评估指标，我们认为这是更合适的建模。我们设计了一个基于偏好的对抗攻击框架，并表明我们的基于NLI的指标比最近基于BERT的指标更强大。在标准基准上，我们的基于NLI的指标的表现优于现有的摘要指标，但在SOTA MT指标下执行。但是，当我们将现有指标与NLI指标相结合时，我们可以获得更高的对抗性鲁棒性（ +20％至 +30％）和较高质量的指标，如标准基准测量（ +5％至 +25％）。

学术研究是解决以前从未解决过的问题的探索活动。通过这种性质，每个学术研究工作都需要进行文献审查，以区分其Novelties尚未通过事先作品解决。在自然语言处理中，该文献综述通常在“相关工作”部分下进行。鉴于研究文件的其余部分和引用的论文列表，自动相关工作生成的任务旨在自动生成“相关工作”部分。虽然这项任务是在10年前提出的，但直到最近，它被认为是作为科学多文件摘要问题的变种。然而，即使在今天，尚未标准化了自动相关工作和引用文本生成的问题。在这项调查中，我们进行了一个元研究，从问题制定，数据集收集，方法方法，绩效评估和未来前景的角度来比较相关工作的现有文献，以便为读者洞察到国家的进步 - 最内容的研究，以及如何进行未来的研究。我们还调查了我们建议未来工作要考虑整合的相关研究领域。

Current metrics for evaluating factuality for abstractive document summarization have achieved high correlations with human judgment, but they do not account for the vision modality and thus are not adequate for vision-and-language summarization. We propose CLIPBERTScore, a simple weighted combination of CLIPScore and BERTScore to leverage the robustness and strong factuality detection performance between image-summary and document-summary, respectively. Next, due to the lack of meta-evaluation benchmarks to evaluate the quality of multimodal factuality metrics, we collect human judgments of factuality with respect to documents and images. We show that this simple combination of two metrics in the zero-shot setting achieves higher correlations than existing factuality metrics for document summarization, outperforms an existing multimodal summarization metric, and performs competitively with strong multimodal factuality metrics specifically fine-tuned for the task. Our thorough analysis demonstrates the robustness and high correlation of CLIPBERTScore and its components on four factuality metric-evaluation benchmarks. Finally, we demonstrate two practical downstream applications of our CLIPBERTScore metric: for selecting important images to focus on during training, and as a reward for reinforcement learning to improve factuality of multimodal summary generation w.r.t automatic and human evaluation. Our data and code are publicly available at https://github.com/meetdavidwan/faithful-multimodal-summ

这项工作适用于最低贝叶斯风险（MBR）解码，以优化翻译质量的各种自动化指标。机器翻译中的自动指标最近取得了巨大的进步。特别是，在人类评级（例如BLEurt，或Comet）上微调，在与人类判断的相关性方面是优于表面度量的微调。我们的实验表明，神经翻译模型与神经基于基于神经参考度量，BLEURT的组合导致自动和人类评估的显着改善。通过与经典光束搜索输出不同的翻译获得该改进：这些翻译的可能性较低，并且较少受到Bleu等表面度量的青睐。

自动摘要评估对于机器生成和人为生产的摘要都有用。自动评估给定文档的摘要文本启用，例如，摘要生成系统开发和检测不适当的摘要。摘要评估可以以多种模式进行：排名摘要生成系统；对特定文档的排名摘要；并在绝对规模上估算文档 - 苏格尔对的质量。带有注释的现有数据集用于摘要评估，通常基于新闻摘要数据集，例如CNN/DailyMail或XSUM。在这项工作中，我们描述了一个新的数据集，即播客摘要评估语料库，这是由TREC2020的人类专家评估的播客摘要集。与现有的摘要评估数据相比，该数据集具有两个独特的方面：（i）基于语音播客的长输入，文档； （ii）有机会在播客语料库中检测不适当的参考摘要。首先，我们检查了现有的评估方法，包括无模型和基于模型的方法，并为此长输入摘要评估数据集提供基准结果。其次，为了过滤参考参考文献配对以进行培训，我们采用摘要评估进行数据选择。这两个方面的实验结果为摘要评估和发电任务提供了有趣的见解。播客摘要评估数据可用。

在序列到序列学习中，例如，自然语言生成，解码器依赖于注意机制，以有效地从编码器中提取信息。虽然常见的做法是从最后一个编码器层绘制信息，但最近的工作已经提出用于使用来自不同编码器层的表示，以进行多样化的信息。尽管如此，解码器仍然仅获得源序列的单个视图，这可能导致由于层级绕过问题而导致编码器层堆栈的训练不足。在这项工作中，我们提出了层次的多视图解码，其中对于每个解码器层以及来自最后一个编码器层的表示，它作为全局视图，来自其他编码器层的那些是用于立体视图的源序列。系统实验和分析表明，我们成功地解决了层次结构绕过问题，需要几乎可忽略的参数增加，并大大提高了五种不同任务的深度表示的序列到序列学习的性能，即机器翻译，抽象总结，图像标题，视频字幕和医疗报告生成。特别是，我们的方法在八个基准数据集中实现了新的最先进的结果，包括低资源机器转换数据集和两个低资源医疗报告生成数据集。

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.

Precisely assessing the progress in natural language generation (NLG) tasks is challenging, and human evaluation to establish a preference in a model's output over another is often necessary. However, human evaluation is usually costly, difficult to reproduce, and non-reusable. In this paper, we propose a new and simple automatic evaluation method for NLG called Near-Negative Distinction (NND) that repurposes prior human annotations into NND tests. In an NND test, an NLG model must place a higher likelihood on a high-quality output candidate than on a near-negative candidate with a known error. Model performance is established by the number of NND tests a model passes, as well as the distribution over task-specific errors the model fails on. Through experiments on three NLG tasks (question generation, question answering, and summarization), we show that NND achieves a higher correlation with human judgments than standard NLG evaluation metrics. We then illustrate NND evaluation in four practical scenarios, for example performing fine-grain model analysis, or studying model training dynamics. Our findings suggest that NND can give a second life to human annotations and provide low-cost NLG evaluation.

文本摘要模型通常经过培训，以产生满足人类质量要求的摘要。但是，现有的摘要文本评估指标只是摘要质量的粗略代理，与人类评分和抑制摘要多样性的相关性低。为了解决这些问题，我们提出了SummScore，这是基于CrossCoder的摘要质量评估的综合指标。首先，通过采用原始的苏格拉外测量模式并比较原始文本的语义，SummScore摆脱了抑制摘要多样性的抑制。借助文本匹配的预训练交叉编码器，SummScore可以有效地捕获摘要语义之间的细微差异。其次，为了提高全面性和解释性，SummScore由四个细粒子模型组成，它们分别测量连贯性，一致性，流利性和相关性。我们使用半监督的多轮训练来提高模型在极有限的注释数据上的性能。广泛的实验表明，与人类评分相关的上述四个维度中，SummScore在上述四个维度中的现有评估指标显着优于现有的评估指标。我们还为16个主流摘要模型提供了SummScore的质量评估结果，以供以后研究。