我们介绍了IST和Unmabel对WMT 2022关于质量估计(QE)的共享任务的共同贡献。我们的团队参与了所有三个子任务:(i)句子和单词级质量预测;(ii)可解释的量化宽松;(iii)关键错误检测。对于所有任务,我们在彗星框架之上构建,将其与OpenKIWI的预测估计架构连接,并为其配备单词级序列标记器和解释提取器。我们的结果表明,在预处理过程中合并参考可以改善下游任务上多种语言对的性能,并且通过句子和单词级别的目标共同培训可以进一步提高。此外,将注意力和梯度信息结合在一起被证明是提取句子级量化量化宽松模型的良好解释的首要策略。总体而言,我们的意见书在几乎所有语言对的所有三个任务中都取得了最佳的结果。
translated by 谷歌翻译
质量估计,作为机器翻译的质量控制的关键步骤,多年来已经探讨过。目标是调查估计机器翻译结果的自动方法而无需参考翻译。在今年的WMT QE共享任务中,我们利用了大规模的XLM-Roberta预训练模型,另外提出了几种有用的功能来评估翻译的不确定性,以构建我们的QE系统,命名为\ texit {qemind}。该系统已应用于直接评估的句子级评分任务和严重错误检测的二进制评分预测任务。在本文中,我们向WMT 2021 QE共享任务提供了我们的提交,并且广泛的实验结果表明我们的多语言系统在WMT 2020的直接评估QE任务中表现出最佳系统。
translated by 谷歌翻译
翻译质量估计(QE)是预测机器翻译(MT)输出质量的任务,而无需任何参考。作为MT实际应用中的重要组成部分,这项任务已越来越受到关注。在本文中,我们首先提出了XLMRScore,这是一种基于使用XLM-Roberta(XLMR)模型计算的BertScore的简单无监督的QE方法,同时讨论了使用此方法发生的问题。接下来,我们建议两种减轻问题的方法:用未知令牌和预训练模型的跨语性对准替换未翻译的单词,以表示彼此之间的一致性单词。我们在WMT21 QE共享任务的四个低资源语言对上评估了所提出的方法,以及本文介绍的新的英语FARSI测试数据集。实验表明,我们的方法可以在两个零射击方案的监督基线中获得可比的结果,即皮尔森相关性的差异少于0.01,同时在所有低资源语言对中的平均低资源语言对中的无人看管竞争对手的平均水平超过8%的平均水平超过8%。 。
translated by 谷歌翻译
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.
translated by 谷歌翻译
State-of-the-art machine translation evaluation metrics are based on black-box language models. Hence, recent works consider their explainability with the goals of better understandability for humans and better metric analysis, including failure cases. In contrast, we explicitly leverage explanations to boost the metrics' performance. In particular, we perceive explanations as word-level scores, which we convert, via power means, into sentence-level scores. We combine this sentence-level score with the original metric to obtain a better metric. Our extensive evaluation and analysis across 5 datasets, 5 metrics and 4 explainability techniques shows that some configurations reliably improve the original metrics' correlation with human judgment. On two held datasets for testing, we obtain improvements in 15/18 resp. 4/4 cases. The gains in Pearson correlation are up to 0.032 resp. 0.055. We make our code available.
translated by 谷歌翻译
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.
translated by 谷歌翻译
监督机器翻译的绝大多数评估指标,即(i)假设参考翻译的存在,(ii)受到人体得分的培训,或(iii)利用并行数据。这阻碍了其适用于此类监督信号的情况。在这项工作中,我们开发了完全无监督的评估指标。为此,我们利用评估指标,平行语料库开采和MT系统之间的相似性和协同作用。特别是,我们使用无监督的评估指标来开采伪并行数据,我们用来重塑缺陷的基础向量空间(以迭代方式),并诱导无监督的MT系统,然后提供伪引用作为伪参考作为在中的附加组件中的附加组件指标。最后,我们还从伪并行数据中诱导无监督的多语言句子嵌入。我们表明,我们完全无监督的指标是有效的,即,他们在5个评估数据集中的4个击败了受监督的竞争对手。
translated by 谷歌翻译
Modern machine learning models are opaque, and as a result there is a burgeoning academic subfield on methods that explain these models' behavior. However, what is the precise goal of providing such explanations, and how can we demonstrate that explanations achieve this goal? Some research argues that explanations should help teach a student (either human or machine) to simulate the model being explained, and that the quality of explanations can be measured by the simulation accuracy of students on unexplained examples. In this work, leveraging meta-learning techniques, we extend this idea to improve the quality of the explanations themselves, specifically by optimizing explanations such that student models more effectively learn to simulate the original model. We train models on three natural language processing and computer vision tasks, and find that students trained with explanations extracted with our framework are able to simulate the teacher significantly more effectively than ones produced with previous methods. Through human annotations and a user study, we further find that these learned explanations more closely align with how humans would explain the required decisions in these tasks. Our code is available at https://github.com/coderpat/learning-scaffold
translated by 谷歌翻译
我们提出了一种两阶段的培训方法,用于开发单个NMT模型,以翻译英语和英语的看不见的语言。对于第一阶段,我们将编码器模型初始化以鉴定XLM-R和Roberta的权重,然后对25种语言的平行数据进行多种语言微调。我们发现该模型可以推广到对看不见的语言的零击翻译。在第二阶段,我们利用这种概括能力从单语数据集生成合成的并行数据,然后用连续的反向翻译训练。最终模型扩展到了英语到许多方向,同时保持了多到英语的性能。我们称我们的方法为ecxtra(以英语为中心的跨语言(x)转移)。我们的方法依次利用辅助并行数据和单语言数据,并且在概念上很简单,仅在两个阶段都使用标准的跨熵目标。最终的ECXTRA模型对8种低资源语言的无监督NMT进行了评估,该语言为英语至哈萨克语(22.3> 10.4 bleu)以及其他15个翻译方向的竞争性能而获得了新的最先进。
translated by 谷歌翻译
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。
translated by 谷歌翻译
机器翻译(MT)的单词级质量估计(QE)旨在在不参考的情况下找出翻译句子中的潜在翻译错误。通常,关于文字级别量化宽松的传统作品旨在根据文章编辑工作来预测翻译质量,其中通过比较MT句子之间的单词来自动生成单词标签(“ OK”和“ BAD”)。通过翻译错误率(TER)工具包编辑的句子。虽然可以使用后编辑的工作来在一定程度上测量翻译质量,但我们发现它通常与人类对单词是否良好或翻译不良的判断相抵触。为了克服限制,我们首先创建了一个金色基准数据集,即\ emph {hjqe}(人类对质量估计的判断),专家翻译直接注释了对其判断的不良翻译单词。此外,为了进一步利用平行语料库,我们提出了使用两个标签校正策略的自我监督的预训练,即标记改进策略和基于树的注释策略,以使基于TER的人工量化量子ceper更接近\ emph {HJQE}。我们根据公开可用的WMT en-de和en-ZH Corpora进行实质性实验。结果不仅表明我们提出的数据集与人类的判断更加一致,而且还确认了提议的标签纠正策略的有效性。 。}
translated by 谷歌翻译
在这项工作中,我们提出了一个系统的实证研究,专注于最先进的多语言编码器在跨越多种不同语言对的交叉语言文档和句子检索任务的适用性。我们首先将这些模型视为多语言文本编码器,并在无监督的ad-hoc句子和文档级CLIR中基准性能。与监督语言理解相比,我们的结果表明,对于无监督的文档级CLIR - 一个没有针对IR特定的微调 - 预训练的多语言编码器的相关性判断,平均未能基于CLWE显着优于早期模型。对于句子级检索,我们确实获得了最先进的性能:然而,通过多语言编码器来满足高峰分数,这些编码器已经进一步专注于监督的时尚,以便句子理解任务,而不是使用他们的香草'现货'变体。在这些结果之后,我们介绍了文档级CLIR的本地化相关性匹配,在那里我们独立地对文件部分进行了查询。在第二部分中,我们评估了在一系列零拍语言和域转移CLIR实验中的英语相关数据中进行微调的微调编码器精细调整的微调我们的结果表明,监督重新排名很少提高多语言变压器作为无监督的基数。最后,只有在域名对比度微调(即,同一域名,只有语言转移),我们设法提高排名质量。我们在目标语言中单次检索的交叉定向检索结果和结果(零拍摄)交叉传输之间的显着实证差异,这指出了在单机数据上训练的检索模型的“单声道过度装备”。
translated by 谷歌翻译
多语种NMT已成为MT在生产中部署的有吸引力的解决方案。但是要匹配双语质量,它符合较大且较慢的型号。在这项工作中,我们考虑了几种方法在推理时更快地使多语言NMT变得更快而不会降低其质量。我们在两种20语言多平行设置中尝试几个“光解码器”架构:在TED会谈中小规模和帕拉克曲线上的大规模。我们的实验表明,将具有词汇过滤的浅解码器组合在于,在翻译质量下没有损失的速度超过两倍。我们用Bleu和Chrf(380语言对),鲁棒性评估和人类评估验证了我们的研究结果。
translated by 谷歌翻译
With the recent advance in neural machine translation demonstrating its importance, research on quality estimation (QE) has been steadily progressing. QE aims to automatically predict the quality of machine translation (MT) output without reference sentences. Despite its high utility in the real world, there remain several limitations concerning manual QE data creation: inevitably incurred non-trivial costs due to the need for translation experts, and issues with data scaling and language expansion. To tackle these limitations, we present QUAK, a Korean-English synthetic QE dataset generated in a fully automatic manner. This consists of three sub-QUAK datasets QUAK-M, QUAK-P, and QUAK-H, produced through three strategies that are relatively free from language constraints. Since each strategy requires no human effort, which facilitates scalability, we scale our data up to 1.58M for QUAK-P, H and 6.58M for QUAK-M. As an experiment, we quantitatively analyze word-level QE results in various ways while performing statistical analysis. Moreover, we show that datasets scaled in an efficient way also contribute to performance improvements by observing meaningful performance gains in QUAK-M, P when adding data up to 1.58M.
translated by 谷歌翻译
This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks. We present mBART -a sequence-to-sequence denoising auto-encoder pre-trained on large-scale monolingual corpora in many languages using the BART objective . mBART is the first method for pre-training a complete sequence-to-sequence model by denoising full texts in multiple languages, while previous approaches have focused only on the encoder, decoder, or reconstructing parts of the text. Pre-training a complete model allows it to be directly fine tuned for supervised (both sentence-level and document-level) and unsupervised machine translation, with no task-specific modifications. We demonstrate that adding mBART initialization produces performance gains in all but the highest-resource settings, including up to 12 BLEU points for low resource MT and over 5 BLEU points for many document-level and unsupervised models. We also show it also enables new types of transfer to language pairs with no bi-text or that were not in the pre-training corpus, and present extensive analysis of which factors contribute the most to effective pre-training.
translated by 谷歌翻译
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.
translated by 谷歌翻译
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。
translated by 谷歌翻译
机器翻译系统(MTS)是通过将文本或语音从一种语言转换为另一种语言的有效工具。在像印度这样的大型多语言环境中,对有效的翻译系统的需求变得显而易见,英语和一套印度语言(ILS)正式使用。与英语相反,由于语料库的不可用,IL仍然被视为低资源语言。为了解决不对称性质,多语言神经机器翻译(MNMT)系统会发展为在这个方向上的理想方法。在本文中,我们提出了一个MNMT系统,以解决与低资源语言翻译有关的问题。我们的模型包括两个MNMT系统,即用于英语印度(一对多),另一个用于指示英语(多一对多),其中包含15个语言对(30个翻译说明)的共享编码器码头。由于大多数IL对具有很少的平行语料库,因此不足以训练任何机器翻译模型。我们探索各种增强策略,以通过建议的模型提高整体翻译质量。最先进的变压器体系结构用于实现所提出的模型。大量数据的试验揭示了其优越性比常规模型的优势。此外,本文解决了语言关系的使用(在方言,脚本等方面),尤其是关于同一家族的高资源语言在提高低资源语言表现方面的作用。此外,实验结果还表明了ILS的倒退和域适应性的优势,以提高源和目标语言的翻译质量。使用所有这些关键方法,我们提出的模型在评估指标方面比基线模型更有效,即一组ILS的BLEU(双语评估研究)得分。
translated by 谷歌翻译
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。
translated by 谷歌翻译
MINED BITEXTS可以包含不完美的翻译,从而产生神经机翻译(NMT)的不可靠的训练信号。在已知过滤这样的对以提高最终模型质量的情况下,我们认为它在低资源条件下是次优的,甚至开采数据可以限制。在我们的工作中,我们提出了通过自动编辑来改进挖掘的BIESTS:给出语言XF中的句子,而且可能是IT XE的不完美翻译,我们的模型生成了一个修订的版本XF'或XE',产生更等值翻译对(即<XF,XE'或<XF',XE>)。我们使用一个简单的编辑策略(1)挖掘在给定的BITExt中的每个句子的潜在不完美的翻译,(2)学习一个模型来重建原始翻译并以多任务方式翻译。实验表明,我们的方法在大多数情况下,在大多数情况下,我们的方法成功地提高了5个低资源语言对和10个翻译方向,在大多数情况下改善了竞争反播基线。
translated by 谷歌翻译