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.

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.

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.

Task-oriented dialogue (TOD) systems have been applied in a range of domains to support human users to achieve specific goals. Systems are typically constructed for a single domain or language and do not generalise well beyond this. Their extension to other languages in particular is restricted by the lack of available training data for many of the world's languages. To support work on Natural Language Understanding (NLU) in TOD across multiple languages and domains simultaneously, we constructed MULTI3NLU++, a multilingual, multi-intent, multi-domain dataset. MULTI3NLU++ extends the English-only NLU++ dataset to include manual translations into a range of high, medium and low resource languages (Spanish, Marathi, Turkish and Amharic), in two domains (banking and hotels). MULTI3NLU++ inherits the multi-intent property of NLU++, where an utterance may be labelled with multiple intents, providing a more realistic representation of a user's goals and aligning with the more complex tasks that commercial systems aim to model. We use MULTI3NLU++ to benchmark state-of-the-art multilingual language models as well as Machine Translation and Question Answering systems for the NLU task of intent detection for TOD systems in the multilingual setting. The results demonstrate the challenging nature of the dataset, particularly in the low-resource language setting.

Much recent progress in applications of machine learning models to NLP has been driven by benchmarks that evaluate models across a wide variety of tasks. However, these broad-coverage benchmarks have been mostly limited to English, and despite an increasing interest in multilingual models, a benchmark that enables the comprehensive evaluation of such methods on a diverse range of languages and tasks is still missing. To this end, we introduce the Cross-lingual TRansfer Evaluation of Multilingual Encoders (XTREME) benchmark, a multi-task benchmark for evaluating the cross-lingual generalization capabilities of multilingual representations across 40 languages and 9 tasks. We demonstrate that while models tested on English reach human performance on many tasks, there is still a sizable gap in the performance of cross-lingually transferred models, particularly on syntactic and sentence retrieval tasks. There is also a wide spread of results across languages. We release the benchmark 1 to encourage research on cross-lingual learning methods that transfer linguistic knowledge across a diverse and representative set of languages and tasks.

Open-Domain Generative Question Answering has achieved impressive performance in English by combining document-level retrieval with answer generation. These approaches, which we refer to as GenQA, can generate complete sentences, effectively answering both factoid and non-factoid questions. In this paper, we extend GenQA to the multilingual and cross-lingual settings. For this purpose, we first introduce GenTyDiQA, an extension of the TyDiQA dataset with well-formed and complete answers for Arabic, Bengali, English, Japanese, and Russian. Based on GenTyDiQA, we design a cross-lingual generative model that produces full-sentence answers by exploiting passages written in multiple languages, including languages different from the question. Our cross-lingual generative system outperforms answer sentence selection baselines for all 5 languages and monolingual generative pipelines for three out of five languages studied.

Translating training data into many languages has emerged as a practical solution for improving cross-lingual transfer. For tasks that involve span-level annotations, such as information extraction or question answering, an additional label projection step is required to map annotated spans onto the translated texts. Recently, a few efforts have utilized a simple mark-then-translate method to jointly perform translation and projection by inserting special markers around the labeled spans in the original sentence. However, as far as we are aware, no empirical analysis has been conducted on how this approach compares to traditional annotation projection based on word alignment. In this paper, we present an extensive empirical study across 42 languages and three tasks (QA, NER, and Event Extraction) to evaluate the effectiveness and limitations of both methods, filling an important gap in the literature. Experimental results show that our optimized version of mark-then-translate, which we call EasyProject, is easily applied to many languages and works surprisingly well, outperforming the more complex word alignment-based methods. We analyze several key factors that affect end-task performance, and show EasyProject works well because it can accurately preserve label span boundaries after translation. We will publicly release all our code and data.

我们介绍了MTG，这是一套新的基准套件，用于培训和评估多语言文本生成。它是具有最大人类通知数据（400K）的第一次传播的多语言多路文本生成数据集。它包括五种语言（英语，德语，法语，西班牙语和中文）的四代任务（故事产生，问题生成，标题生成和文本摘要）。Multiway设置可以启用跨语言和任务的模型测试知识传输功能。使用MTG，我们从不同方面训练和分析了几种流行的多语言生成模型。我们的基准套件通过更多的人为宣传的并行数据促进了模型性能增强。它提供了各种一代方案的全面评估。代码和数据可在\ url {https://github.com/zide05/mtg}上获得。

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.

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。

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.

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。

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％。 。

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％）。

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。

Semantic Textual Similarity (STS) measures the meaning similarity of sentences. Applications include machine translation (MT), summarization, generation, question answering (QA), short answer grading, semantic search, dialog and conversational systems. The STS shared task is a venue for assessing the current state-of-the-art. The 2017 task focuses on multilingual and cross-lingual pairs with one sub-track exploring MT quality estimation (MTQE) data. The task obtained strong participation from 31 teams, with 17 participating in all language tracks. We summarize performance and review a selection of well performing methods. Analysis highlights common errors, providing insight into the limitations of existing models. To support ongoing work on semantic representations, the STS Benchmark is introduced as a new shared training and evaluation set carefully selected from the corpus of English STS shared task data (2012-2017). 7 We use 50-dimensional GloVe word embeddings (Pennington et al., 2014) trained on a combination of Gigaword 5 (Parker et al., 2011) and English Wikipedia available at http://nlp.stanford.edu/projects/glove/.8 https://www.mturk.com/ 9 A designation that statistically identifies workers who perform high quality work across a diverse set of tasks.10 Spanish data from 2015 and 2014 uses a 5 point scale that collapses STS labels 4 and 3, removing the distinction between unimportant and important details.

在本文中，我们分享了我们努力建立能够翻译一千多种语言的实用机器翻译（MT）系统的发现。我们在三个研究领域中描述了结果：（i）通过利用半监督预训练的语言识别和开发数据驱动的过滤技术来构建1500多种语言的清洁，网挖数据集； （ii）通过利用大规模的多语言模型来开发用于服务不足的语言的实用MT模型，该模型训练了有监督的并行数据，以使用100多种高资源语言和单语言数据集，以增加1000多种语言； （iii）研究这些语言的评估指标的局限性，并对我们MT模型的输出进行定性分析，突出显示了这些类型模型的几种频繁误差模式。我们希望我们的工作为旨在为当前研究的语言构建MT系统的从业者提供有用的见解，并突出显示可以补充Data-Sparse设置中大量多语言模型的弱点的研究方向。

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.

针对任务导向的对话系统的强大状态跟踪目前仍然限于一些流行语言。本文显示，给定以一种语言设置的大规模对话数据，我们可以使用机器翻译自动为其他语言生成有效的语义解析器。我们提出了对话数据集的自动翻译，并进行对齐，以确保插槽值的忠实翻译，并消除以前的基准中使用的昂贵人类监督。我们还提出了一种新的上下文语义解析模型，它编码正式的插槽和值，只有最后一个代理和用户话语。我们表明，简洁的表示降低了翻译误差的复合效果，而不会损害实践中的准确性。我们评估我们对几个对话状态跟踪基准的方法。在Risawoz，Crosswoz，Crosswoz-Zh和Multiwoz-Zh Datasets，我们将最先进的技术提高11％，17％，20％和0.3％，以共同的目标准确度。我们为所有三个数据集提供了全面的错误分析，显示错误注释可以模糊模型质量的判断。最后，我们使用推荐方法创建了Risawoz英语和德语数据集。在这些数据集中，准确性在原始的11％以内，表示可能的高精度多语言对话数据集，而无需依赖昂贵的人类注释。

估计机器翻译系统的质量是该领域的研究人员的持续挑战。许多以前使用往返翻译的尝试作为质量的衡量标准失败，并且对其是一种可行的质量估算方法有很大的分歧。在本文中，我们重新审视了往返翻译，提出了一个旨在解决这种方法发现的先前陷阱的系统。我们的方法利用近期语言表示的进步学习，以更准确地衡量原始和往返翻译句子之间的相似性。实验表明，虽然我们的方法没有达到现有技术的当前状态的性能，但它仍然可能是某些语言对的有效方法。