人类评估一直昂贵，而研究人员则努力信任自动指标。为了解决这个问题，我们建议通过采取预先接受训练的语言模型（PLM）和有限的人类标记分数来定制传统指标。我们首先重新介绍Hlepor度量因子，然后是我们开发的Python版本（移植），这实现了Hlepor度量中的加权参数的自动调整。然后我们介绍了使用Optuna超参数优化框架的定制Hlepor（Cushlepor），以便更好地协议为预先接受训练的语言模型（使用Labse），这是关于Cushlepor的确切MT语言对。我们还在英语 - 德语和汉英语言对基于MQM和PSQM框架的专业人体评估数据进行了优化的曲位波。实验研究表明，Cushlepor可以提升Hlepor对PLMS的更好的表演，如Labse，如Labse的更好的成本，以及更好的人类评估协议，包括MQM和PSQM得分，并且比Bleu（AT \ URL的数据提供更好的表演（HTTPS：// github.com/poethan/cushlepor}）。官方结果表明，我们的提交赢得了三种语言对，包括\ textbf {英语 - 德语}和\ textbf {中文 - 英文}通过cushlepor（lm）和\ textbf {英语 - 俄语}上\ textit {通过hlepor ted}域。

预训练的语言模型（PLM）通常会利用单语和多语言数据集的优势，该数据集可以在线免费获得，以在部署到特定任务中之前获取一般或混合域知识。最近提出了超大型PLM（XLPLM），以声称对较小尺寸的PLM（例如机器翻译（MT）任务）声称最高性能。这些XLPLM包括Meta-AI的WMT21密度24宽-EN-X和NLLB。 \ textIt {在这项工作中，我们检查XLPLM是否绝对优于较小尺寸的PLM，在针对特定域的MTS中进行微调。}我们使用了不同大小的两个不同的内域数据：商业自动化内部数据和\ textbf {临床}在WMT2022上共享了Clinspen2022挑战的任务数据。我们选择受欢迎的玛丽安·赫尔辛基（Marian Helsinki）作为较小尺寸的PLM和来自Meta-AI的两个大型大型转换器作为XLPLM。我们的实验研究表明，1）在较小尺寸的内域商业汽车数据上，XLPLM WMT21密度24宽24宽-EN-X确实显示出使用S \ TextSc {acre} BLEU和HLEU指标的评估得分要好得多。玛丽安（Marian），即使其得分提高率低于微调后的玛丽安（Marian）； 2）在相对较大尺寸的精心准备的临床数据微调上，XLPLM NLLB \ textbf {倾向于失去}其优于较小尺寸的Marian在两个子任务（临床术语和本体概念）上使用Clinspen提供的指标Meteor，Meteor，Marian的优势。 Comet和Rouge-L，并且在所有指标上完全输给了Marian，包括S \ textsc {acre} bleu and Bleu； 3）\ textbf {指标并不总是同意}在相同的任务上使用相同的模型输出相互同意。

As machine translation (MT) metrics improve their correlation with human judgement every year, it is crucial to understand the limitations of such metrics at the segment level. Specifically, it is important to investigate metric behaviour when facing accuracy errors in MT because these can have dangerous consequences in certain contexts (e.g., legal, medical). We curate ACES, a translation accuracy challenge set, consisting of 68 phenomena ranging from simple perturbations at the word/character level to more complex errors based on discourse and real-world knowledge. We use ACES to evaluate a wide range of MT metrics including the submissions to the WMT 2022 metrics shared task and perform several analyses leading to general recommendations for metric developers. We recommend: a) combining metrics with different strengths, b) developing metrics that give more weight to the source and less to surface-level overlap with the reference and c) explicitly modelling additional language-specific information beyond what is available via multilingual embeddings.

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.

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.

We present the task of PreQuEL, Pre-(Quality-Estimation) Learning. A PreQuEL system predicts how well a given sentence will be translated, without recourse to the actual translation, thus eschewing unnecessary resource allocation when translation quality is bound to be low. PreQuEL can be defined relative to a given MT system (e.g., some industry service) or generally relative to the state-of-the-art. From a theoretical perspective, PreQuEL places the focus on the source text, tracing properties, possibly linguistic features, that make a sentence harder to machine translate. We develop a baseline model for the task and analyze its performance. We also develop a data augmentation method (from parallel corpora), that improves results substantially. We show that this augmentation method can improve the performance of the Quality-Estimation task as well. We investigate the properties of the input text that our model is sensitive to, by testing it on challenge sets and different languages. We conclude that it is aware of syntactic and semantic distinctions, and correlates and even over-emphasizes the importance of standard NLP features.

我们假设现有的句子级机器翻译（MT）指标在人类参考包含歧义时会效率降低。为了验证这一假设，我们提出了一种非常简单的方法，用于扩展预审计的指标以在文档级别合并上下文。我们将我们的方法应用于三个流行的指标，即Bertscore，Prism和Comet，以及无参考的公制Comet-QE。我们使用提供的MQM注释评估WMT 2021指标共享任务的扩展指标。我们的结果表明，扩展指标的表现在约85％的测试条件下优于其句子级别的级别，而在排除低质量人类参考的结果时。此外，我们表明我们的文档级扩展大大提高了其对话语现象任务的准确性，从而优于专用基线高达6.1％。我们的实验结果支持我们的初始假设，并表明对指标的简单扩展使他们能够利用上下文来解决参考中的歧义。

End-to-End speech-to-speech translation (S2ST) is generally evaluated with text-based metrics. This means that generated speech has to be automatically transcribed, making the evaluation dependent on the availability and quality of automatic speech recognition (ASR) systems. In this paper, we propose a text-free evaluation metric for end-to-end S2ST, named BLASER, to avoid the dependency on ASR systems. BLASER leverages a multilingual multimodal encoder to directly encode the speech segments for source input, translation output and reference into a shared embedding space and computes a score of the translation quality that can be used as a proxy to human evaluation. To evaluate our approach, we construct training and evaluation sets from more than 40k human annotations covering seven language directions. The best results of BLASER are achieved by training with supervision from human rating scores. We show that when evaluated at the sentence level, BLASER correlates significantly better with human judgment compared to ASR-dependent metrics including ASR-SENTBLEU in all translation directions and ASR-COMET in five of them. Our analysis shows combining speech and text as inputs to BLASER does not increase the correlation with human scores, but best correlations are achieved when using speech, which motivates the goal of our research. Moreover, we show that using ASR for references is detrimental for text-based metrics.

Modern embedding-based metrics for evaluation of generated text generally fall into one of two paradigms: discriminative metrics that are trained to directly predict which outputs are of higher quality according to supervised human annotations, and generative metrics that are trained to evaluate text based on the probabilities of a generative model. Both have their advantages; discriminative metrics are able to directly optimize for the problem of distinguishing between good and bad outputs, while generative metrics can be trained using abundant raw text. In this paper, we present a framework that combines the best of both worlds, using both supervised and unsupervised signals from whatever data we have available. We operationalize this idea by training T5Score, a metric that uses these training signals with mT5 as the backbone. We perform an extensive empirical comparison with other existing metrics on 5 datasets, 19 languages and 280 systems, demonstrating the utility of our method. Experimental results show that: T5Score achieves the best performance on all datasets against existing top-scoring metrics at the segment level. We release our code and models at https://github.com/qinyiwei/T5Score.

评估指标是文本生成系统的关键成分。近年来，已经提出了几十年前的文本生成质量的人类评估，提出了几个基于伯特的评估指标（包括Bertscore，Moverscore，BLEurt等），这些评估与文本生成质量的人类评估比Bleu或Rouge进行了更好。但是，很少是已知这些度量基于黑盒语言模型表示的指标实际捕获（通常假设它们模型语义相似性）。在这项工作中，我们使用基于简单的回归的全局解释技术来沿着语言因素解开度量标准分数，包括语义，语法，形态和词汇重叠。我们表明，不同的指标捕获了一定程度的各个方面，但它们对词汇重叠大大敏感，就像Bleu和Rouge一样。这暴露了这些新颖性拟议的指标的限制，我们还在对抗对抗测试场景中突出显示。

我们为机器翻译（MT）评估发布了70个小鉴别的测试集，称为方差感知测试集（VAT），从WMT16覆盖了35个翻译方向到WMT20竞争。VAT由一种新颖的方差感知过滤方法自动创建，该方法会在没有任何人工的情况下过滤当前MT测试集的不分度测试实例。实验结果表明，VAT在主流语言对和测试集中与人为判断的相关性方面优于原始的WMT测试集。进一步分析增值税的性质揭示了竞争MT系统的具有挑战性的语言特征（例如，低频词和专有名词），为构建未来MT测试集提供指导。测试集和准备方差感知MT测试集的代码可在https://github.com/nlp2ct/variance-aware-mt-test-sets自由使用。

With the fast development of Machine Translation (MT) systems, especially the new boost from Neural MT (NMT) models, the MT output quality has reached a new level of accuracy. However, many researchers criticised that the current popular evaluation metrics such as BLEU can not correctly distinguish the state-of-the-art NMT systems regarding quality differences. In this short paper, we describe the design and implementation of a linguistically motivated human-in-the-loop evaluation metric looking into idiomatic and terminological Multi-word Expressions (MWEs). MWEs have played a bottleneck in many Natural Language Processing (NLP) tasks including MT. MWEs can be used as one of the main factors to distinguish different MT systems by looking into their capabilities in recognising and translating MWEs in an accurate and meaning equivalent manner.

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。

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％）。

Large language models (LLMs) that have been trained on multilingual but not parallel text exhibit a remarkable ability to translate between languages. We probe this ability in an in-depth study of the pathways language model (PaLM), which has demonstrated the strongest machine translation (MT) performance among similarly-trained LLMs to date. We investigate various strategies for choosing translation examples for few-shot prompting, concluding that example quality is the most important factor. Using optimized prompts, we revisit previous assessments of PaLM's MT capabilities with more recent test sets, modern MT metrics, and human evaluation, and find that its performance, while impressive, still lags that of state-of-the-art supervised systems. We conclude by providing an analysis of PaLM's MT output which reveals some interesting properties and prospects for future work.

We describe METEOR, an automatic metric for machine translation evaluation that is based on a generalized concept of unigram matching between the machineproduced translation and human-produced reference translations. Unigrams can be matched based on their surface forms, stemmed forms, and meanings; furthermore, METEOR can be easily extended to include more advanced matching strategies.Once all generalized unigram matches between the two strings have been found, METEOR computes a score for this matching using a combination of unigram-precision, unigram-recall, and a measure of fragmentation that is designed to directly capture how well-ordered the matched words in the machine translation are in relation to the reference. We evaluate METEOR by measuring the correlation between the metric scores and human judgments of translation quality. We compute the Pearson R correlation value between its scores and human quality assessments of the LDC TIDES 2003 Arabic-to-English and Chinese-to-English datasets.We perform segment-bysegment correlation, and show that METEOR gets an R correlation value of 0.347 on the Arabic data and 0.331 on the Chinese data. This is shown to be an improvement on using simply unigramprecision, unigram-recall and their harmonic F1 combination. We also perform experiments to show the relative contributions of the various mapping modules.

通常需要平行语料库来使用BLEU，流星和Bertscore等指标自动评估翻译质量。尽管基于参考的评估范式被广泛用于许多机器翻译任务中，但由于这些语言遭受了语料库的不足，因此很难将其应用于使用低资源语言的翻译。往返翻译提供了一种令人鼓舞的方法来减轻平行语料库的紧急要求，尽管不幸的是，在统计机器翻译时代，没有观察到与转发翻译相关。在本文中，我们首先观察到，正向翻译质量始终与神经机器翻译范围中相应的往返翻译质量相关。然后，我们仔细分析并揭示了统计机器翻译系统上矛盾结果的原因。其次，我们提出了一种简单而有效的回归方法，以根据各种语言对的往返翻译分数（包括非常低的资源语言之间的往返翻译得分）来预测前向翻译得分的性能。我们进行了广泛的实验，以显示1,000多个语言对的预测模型的有效性和鲁棒性。最后，我们测试了有关挑战性设置的方法，例如预测分数：i）在培训中看不见的语言对，ii）在现实世界中，WMT共享任务但在新领域中。广泛的实验证明了我们方法的鲁棒性和效用。我们相信我们的工作将激发有关非常低资源的多语言机器翻译的工作。

在任何翻译工作流程中，从源到目标的域知识保存至关重要。在翻译行业中，接收高度专业化的项目是很常见的，那里几乎没有任何平行的内域数据。在这种情况下，没有足够的内域数据来微调机器翻译（MT）模型，生成与相关上下文一致的翻译很具有挑战性。在这项工作中，我们提出了一种新颖的方法，用于域适应性，以利用最新的审计语言模型（LMS）来用于特定于域的MT的域数据增强，并模拟（a）的（a）小型双语数据集的域特征，或（b）要翻译的单语源文本。将这个想法与反翻译相结合，我们可以为两种用例生成大量的合成双语内域数据。为了进行调查，我们使用最先进的变压器体系结构。我们采用混合的微调来训练模型，从而显着改善了内域文本的翻译。更具体地说，在这两种情况下，我们提出的方法分别在阿拉伯语到英语对阿拉伯语言对上分别提高了大约5-6个BLEU和2-3 BLEU。此外，人类评估的结果证实了自动评估结果。

Automatic machine translation (MT) metrics are widely used to distinguish the translation qualities of machine translation systems across relatively large test sets (system-level evaluation). However, it is unclear if automatic metrics are reliable at distinguishing good translations from bad translations at the sentence level (segment-level evaluation). In this paper, we investigate how useful MT metrics are at detecting the success of a machine translation component when placed in a larger platform with a downstream task. We evaluate the segment-level performance of the most widely used MT metrics (chrF, COMET, BERTScore, etc.) on three downstream cross-lingual tasks (dialogue state tracking, question answering, and semantic parsing). For each task, we only have access to a monolingual task-specific model. We calculate the correlation between the metric's ability to predict a good/bad translation with the success/failure on the final task for the Translate-Test setup. Our experiments demonstrate that all metrics exhibit negligible correlation with the extrinsic evaluation of the downstream outcomes. We also find that the scores provided by neural metrics are not interpretable mostly because of undefined ranges. Our analysis suggests that future MT metrics be designed to produce error labels rather than scores to facilitate extrinsic evaluation.

The rapid growth of machine translation (MT) systems has necessitated comprehensive studies to meta-evaluate evaluation metrics being used, which enables a better selection of metrics that best reflect MT quality. Unfortunately, most of the research focuses on high-resource languages, mainly English, the observations for which may not always apply to other languages. Indian languages, having over a billion speakers, are linguistically different from English, and to date, there has not been a systematic study of evaluating MT systems from English into Indian languages. In this paper, we fill this gap by creating an MQM dataset consisting of 7000 fine-grained annotations, spanning 5 Indian languages and 7 MT systems, and use it to establish correlations between annotator scores and scores obtained using existing automatic metrics. Our results show that pre-trained metrics, such as COMET, have the highest correlations with annotator scores. Additionally, we find that the metrics do not adequately capture fluency-based errors in Indian languages, and there is a need to develop metrics focused on Indian languages. We hope that our dataset and analysis will help promote further research in this area.