Recent large language models (LLM) areleveraging human feedback to improve theirgeneration quality. However, human feedbackis costly to obtain, especially during inference.In this work, we propose LLMRefine, aninference time optimization method to refineLLM’s output. The core idea is to usea learned fine-grained feedback model topinpoint defects and guide LLM to refinethem iteratively. Using original LLM as aproposal of edits, LLMRefine searches fordefect-less text via simulated annealing, tradingoff the exploration and exploitation. Weconduct experiments on three text generationtasks, including machine translation, long-form question answering (QA), and topicalsummarization. LLMRefine consistentlyoutperforms all baseline approaches, achievingimprovements up to 1.7 MetricX points ontranslation tasks, 8.1 ROUGE-L on ASQA, 2.2ROUGE-L on topical summarization.

Reliable human evaluation is critical to the development of successful natural language generation models, but achieving it is notoriously difficult. Stability is a crucial requirement when ranking systems by quality: consistent ranking of systems across repeated evaluations is not just desirable, but essential. Without it, there is no reliable foundation for hill-climbing or product launch decisions. In this paper, we use machine translation and its state-of-the-art human evaluation framework, MQM, as a case study to understand how to set up reliable human evaluations that yield stable conclusions. We investigate the optimal configurations for item allocation to raters, number of ratings per item, and score normalization. Our study on two language pairs provides concrete recommendations for designing replicable human evaluation studies. We also collect and release the largest publicly available dataset of multi-segment translations rated by multiple professional translators, consisting of nearly 140,000 segment annotations across two language pairs.

This overview paper presents the results of the General Machine Translation Task organised as part of the 2024 Conference on Machine Translation (WMT). In the general MT task, participants were asked to build machine translation systems for any of 11 language pairs, to be evaluated on test sets consisting of three to five different domains. In addition to participating systems, we collected translations from 8 different large language models (LLMs) and 4 online translation providers. We evaluate system outputs with professional human annotators using a new protocol called Error Span Annotations (ESA).

The WMT24 Metrics Shared Task evaluated the performance of automatic metrics for machine translation (MT), with a major focus on LLM-based translations that were generated as part of the WMT24 General MT Shared Task. As LLMs become increasingly popular in MT, it is crucial to determine whether existing evaluation metrics can accurately assess the output of these systems.To provide a robust benchmark for this evaluation, human assessments were collected using Multidimensional Quality Metrics (MQM), continuing the practice from recent years. Furthermore, building on the success of the previous year, a challenge set subtask was included, requiring participants to design contrastive test suites that specifically target a metric’s ability to identify and penalize different types of translation errors.Finally, the meta-evaluation procedure was refined to better reflect real-world usage of MT metrics, focusing on pairwise accuracy at both the system- and segment-levels.We present an extensive analysis on how well metrics perform on three language pairs: English to Spanish (Latin America), Japanese to Chinese, and English to German. The results strongly confirm the results reported last year, that fine-tuned neural metrics continue to perform well, even when used to evaluate LLM-based translation systems.

We report the results of the WMT 2024 shared task on Quality Estimation, in which the challenge is to predict the quality of the output of neural machine translation systems at the word and sentence levels, without access to reference translations. In this edition, we expanded our scope to assess the potential for quality estimates to help in the correction of translated outputs, hence including an automated post-editing (APE) direction. We publish new test sets with human annotations that target two directions: providing new Multidimensional Quality Metrics (MQM) annotations for three multi-domain language pairs (English to German, Spanish and Hindi) and extending the annotations on Indic languages providing direct assessments and post edits for translation from English into Hindi, Gujarati, Tamil and Telugu. We also perform a detailed analysis of the behaviour of different models with respect to different phenomena including gender bias, idiomatic language, and numerical and entity perturbations. We received submissions based both on traditional, encoder-based approaches as well as large language model (LLM) based ones.

In this paper, we present the MetricX-24 submissions to the WMT24 Metrics Shared Task and provide details on the improvements we made over the previous version of MetricX. Our primary submission is a hybrid reference-based/-free metric, which can score a translation irrespective of whether it is given the source segment, the reference, or both. The metric is trained on previous WMT data in a two-stage fashion, first on the DA ratings only, then on a mixture of MQM and DA ratings. The training set in both stages is augmented with synthetic examples that we created to make the metric more robust to several common failure modes, such as fluent but unrelated translation, or undertranslation. We demonstrate the benefits of the individual modifications via an ablation study, and show a significant performance increase over MetricX-23 on the WMT23 MQM ratings, as well as our new synthetic challenge set.

While Minimum Bayes Risk (MBR) decoding using metrics such as COMET or MetricX has outperformed traditional decoding methods such as greedy or beam search, it introduces a challenge we refer to as metric bias. As MBR decoding aims to produce translations that score highly according to a specific utility metric, this very process makes it impossible to use the same metric for both decoding and evaluation, as any improvement might simply be due to reward hacking rather than reflecting real quality improvements. In this work we demonstrate that compared to human ratings, neural metrics not only overestimate the quality of MBR decoding when the same metric is used as the utility metric, but they also overestimate the quality of MBR/QE decoding with other neural utility metrics as well. We also show that the metric bias issue can be mitigated by using an ensemble of utility metrics during MBR decoding: human evaluations show that MBR decoding using an ensemble of utility metrics outperforms a single utility metric.

Collecting high-quality translations is crucial for the development and evaluation of machine translation systems. However, traditional human-only approaches are costly and slow. This study presents a comprehensive investigation of 11 approaches for acquiring translation data, including human-only, machine-only, and hybrid approaches. Our findings demonstrate that human-machine collaboration can match or even exceed the quality of human-only translations, while being more cost-efficient. Error analysis reveals the complementary strengths between human and machine contributions, highlighting the effectiveness of collaborative methods. Cost analysis further demonstrates the economic benefits of human-machine collaboration methods, with some approaches achieving top-tier quality at around 60% of the cost of traditional methods. We release a publicly available dataset containing nearly 18,000 segments of varying translation quality with corresponding human ratings to facilitate future research.

In this paper we present a step-by-step approach to long-form text translation, drawing on established processes in translation studies. Instead of viewing machine translation as a single, monolithic task, we propose a framework that engages language models in a multi-turn interaction, encompassing pre-translation research, drafting, refining, and proofreading, resulting in progressively improved translations.Extensive automatic evaluations using Gemini 1.5 Pro across ten language pairs show that translating step-by-step yields large translation quality improvements over conventional zero-shot prompting approaches and earlier human-like baseline strategies, resulting in state-of-the-art results on WMT 2024.

Recent research in neural machine translation (NMT) has shown that training on high-quality machine-generated data can outperform training on human-generated data. This work accompanies the first-ever release of a LLM-generated, MBR-decoded and QE-reranked dataset with both sentence-level and multi-sentence examples. We perform extensive experiments to demonstrate the quality of our dataset in terms of its downstream impact on NMT model performance. We find that training from scratch on our (machine-generated) dataset outperforms training on the (web-crawled) WMT’23 training dataset (which is 300 times larger), and also outperforms training on the top-quality subset of the WMT’23 training dataset. We also find that performing self-distillation by finetuning the LLM which generated this dataset outperforms the LLM’s strong few-shot baseline. These findings corroborate the quality of our dataset, and demonstrate the value of high-quality machine-generated data in improving performance of NMT models.

Maximum-a-posteriori (MAP) decoding is the most widely used decoding strategy for neural machine translation (NMT) models. The underlying assumption is that model probability correlates well with human judgment, with better translations getting assigned a higher score by the model. However, research has shown that this assumption does not always hold, and generation quality can be improved by decoding to optimize a utility function backed by a metric or quality-estimation signal, as is done by Minimum Bayes Risk (MBR) or Quality-Aware decoding. The main disadvantage of these approaches is that they require an additional model to calculate the utility function during decoding, significantly increasing the computational cost. In this paper, we propose to make the NMT models themselves quality-aware by training them to estimate the quality of their own output. Using this approach for MBR decoding we can drastically reduce the size of the candidate list, resulting in a speed-up of two-orders of magnitude. When applying our method to MAP decoding we obtain quality gains similar or even superior to quality reranking approaches, but with the efficiency of single pass decoding.

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.

Recent advances in machine translation (MT) have shown that Minimum Bayes Risk (MBR) decoding can be a powerful alternative to beam search decoding, especially when combined with neural-based utility functions. However, the performance of MBR decoding depends heavily on how and how many candidates are sampled from the model. In this paper, we explore how different sampling approaches for generating candidate lists for MBR decoding affect performance. We evaluate popular sampling approaches, such as ancestral, nucleus, and top-k sampling. Based on our insights into their limitations, we experiment with the recently proposed epsilon-sampling approach, which prunes away all tokens with a probability smaller than epsilon, ensuring that each token in a sample receives a fair probability mass. Through extensive human evaluations, we demonstrate that MBR decoding based on epsilon-sampling significantly outperforms not only beam search decoding, but also MBR decoding with all other tested sampling methods across four language pairs.

Automatically evaluating the quality of language generation is critical. Although recent learned metrics show high correlation with human judgement, these metrics do not provide explicit explanation of their verdict, nor associate the scores with defects in the generated text. To address this limitation, we present INSTRUCTSCORE, a fine-grained explainable evaluation metric for text generation. By harnessing both explicit human instruction and the implicit knowledge of GPT-4, we fine-tune a text evaluation metric based on LLaMA, producing both a score for generated text and a human readable diagnostic report. We evaluate INSTRUCTSCORE on a variety of generation tasks, including translation, captioning, data-to-text, and commonsense generation. Experiments show that our 7B model surpasses all other unsupervised metrics, including those based on 175B GPT-3 and GPT-4. Surprisingly, our INSTRUCTSCORE, even without direct supervision from human-rated data, achieves performance levels on par with state-of-the-art metrics like COMET22, which were fine-tuned on human ratings.

Kendall’s tau is frequently used to meta-evaluate how well machine translation (MT) evaluation metrics score individual translations. Its focus on pairwise score comparisons is intuitive but raises the question of how ties should be handled, a gray area that has motivated different variants in the literature. We demonstrate that, in settings like modern MT meta-evaluation, existing variants have weaknesses arising from their handling of ties, and in some situations can even be gamed. We propose instead to meta-evaluate metrics with a version of pairwise accuracy that gives metrics credit for correctly predicting ties, in combination with a tie calibration procedure that automatically introduces ties into metric scores, enabling fair comparison between metrics that do and do not predict ties. We argue and provide experimental evidence that these modifications lead to fairer ranking-based assessments of metric performance.

This paper presents the results of the General Machine Translation Task organised as part of the 2023 Conference on Machine Translation (WMT). In the general MT task, participants were asked to build machine translation systems for any of 8 language pairs (corresponding to 14 translation directions), to be evaluated on test sets consisting of up to four different domains. We evaluate system outputs with professional human annotators using a combination of source-based Direct Assessment and scalar quality metric (DA+SQM).

Quality Estimation (QE), the evaluation of machine translation output without the need of explicit references, has seen big improvements in the last years with the use of neural metrics. In this paper we analyze the viability of using QE metrics for filtering out bad quality sentence pairs in the training data of neural machine translation systems (NMT). While most corpus filtering methods are focused on detecting noisy examples in collections of texts, usually huge amounts of web crawled data, QE models are trained to discriminate more fine-grained quality differences. We show that by selecting the highest quality sentence pairs in the training data, we can improve translation quality while reducing the training size by half. We also provide a detailed analysis of the filtering results, which highlights the differences between both approaches.

This paper presents the results of the WMT23 Metrics Shared Task. Participants submitting automatic MT evaluation metrics were asked to score the outputs of the translation systems competing in the WMT23 News Translation Task. All metrics were evaluated on how well they correlate with human ratings at the system and segment level. Similar to last year, we acquired our own human ratings based on expert-based human evaluation via Multidimensional Quality Metrics (MQM). Following last year’s success, we also included a challenge set subtask, where participants had to create contrastive test suites for evaluating metrics’ ability to capture and penalise specific types of translation errors. Furthermore, we improved our meta-evaluation procedure by considering fewer tasks and calculating a global score by weighted averaging across the various tasks. We present an extensive analysis on how well metrics perform on three language pairs: Chinese-English, Hebrew-English on the sentence-level and English-German on the paragraph-level. The results strongly confirm the results reported last year, that neural-based metrics are significantly better than non-neural metrics in their levels of correlation with human judgments. Further, we investigate the impact of bad reference translations on the correlations of metrics with human judgment. We present a novel approach for generating synthetic reference translations based on the collection of MT system outputs and their corresponding MQM ratings, which has the potential to mitigate bad reference issues we observed this year for some language pairs. Finally, we also study the connections between the magnitude of metric differences and their expected significance in human evaluation, which should help the community to better understand and adopt new metrics.

We present the results from the 9th round of the WMT shared task on MT Automatic Post-Editing, which consists of automatically correcting the output of a “black-box” machine translation system by learning from human corrections. Like last year, the task focused on English→Marathi, with data coming from multiple domains (healthcare, tourism, and general/news). Despite the consistent task framework, this year’s data proved to be extremely challenging. As a matter of fact, none of the official submissions from the participating teams succeeded in improving the quality of the already high-level initial translations (with baseline TER and BLEU scores of 26.6 and 70.66, respectively). Only one run, accepted as a “late” submission, achieved automatic evaluation scores that exceeded the baseline.

This report details the MetricX-23 submission to the WMT23 Metrics Shared Task and provides an overview of the experiments that informed which metrics were submitted. Our 3 submissions—each with a quality estimation (or reference-free) version—are all learned regression-based metrics that vary in the data used for training and which pretrained language model was used for initialization. We report results related to understanding (1) which supervised training data to use, (2) the impact of how the training labels are normalized, (3) the amount of synthetic training data to use, (4) how metric performance is related to model size, and (5) the effect of initializing the metrics with different pretrained language models. The most successful training recipe for MetricX employs two-stage fine-tuning on DA and MQM ratings, and includes synthetic training data. Finally, one important takeaway from our extensive experiments is that optimizing for both segment- and system-level performance at the same time is a challenging task.

This report describes the Minimum Bayes Risk Quality Estimation (MBR-QE) submission to the Workshop on Machine Translation’s 2023 Metrics Shared Task. MBR decoding with neural utility metrics like BLEURT is known to be effective in generating high quality machine translations. We use the underlying technique of MBR decoding and develop an MBR based reference-free quality estimation metric. Our method uses an evaluator machine translation system and a reference-based utility metric (specifically BLEURT and MetricX) to calculate a quality estimation score of a model. We report results related to comparing different MBR configurations and utility metrics.

As research on machine translation moves to translating text beyond the sentence level, it remains unclear how effective automatic evaluation metrics are at scoring longer translations. In this work, we first propose a method for creating paragraph-level data for training and meta-evaluating metrics from existing sentence-level data. Then, we use these new datasets to benchmark existing sentence-level metrics as well as train learned metrics at the paragraph level. Interestingly, our experimental results demonstrate that using sentence-level metrics to score entire paragraphs is equally as effective as using a metric designed to work at the paragraph level. We speculate this result can be attributed to properties of the task of reference-based evaluation as well as limitations of our datasets with respect to capturing all types of phenomena that occur in paragraph-level translations.

Automatic evaluation of machine translation (MT) is a critical tool driving the rapid iterative development of MT systems. While considerable progress has been made on estimating a single scalar quality score, current metrics lack the informativeness of more detailed schemes that annotate individual errors, such as Multidimensional Quality Metrics (MQM). In this paper, we help fill this gap by proposing AutoMQM, a prompting technique which leverages the reasoning and in-context learning capabilities of large language models (LLMs) and asks them to identify and categorize errors in translations. We start by evaluating recent LLMs, such as PaLM and PaLM-2, through simple score prediction prompting, and we study the impact of labeled data through in-context learning and finetuning. We then evaluate AutoMQM with PaLM-2 models, and we find that it improves performance compared to just prompting for scores (with particularly large gains for larger models) while providing interpretability through error spans that align with human annotations.

Modern unsupervised machine translation (MT) systems reach reasonable translation quality under clean and controlled data conditions. As the performance gap between supervised and unsupervised MT narrows, it is interesting to ask whether the different training methods result in systematically different output beyond what is visible via quality metrics like adequacy or BLEU. We compare translations from supervised and unsupervised MT systems of similar quality, finding that unsupervised output is more fluent and more structurally different in comparison to human translation than is supervised MT. We then demonstrate a way to combine the benefits of both methods into a single system which results in improved adequacy and fluency as rated by human evaluators. Our results open the door to interesting discussions about how supervised and unsupervised MT might be different yet mutually-beneficial.

Human-translated text displays distinct features from naturally written text in the same language. This phenomena, known as translationese, has been argued to confound the machine translation (MT) evaluation. Yet, we find that existing work on translationese neglects some important factors and the conclusions are mostly correlational but not causal. In this work, we collect CausalMT, a dataset where the MT training data are also labeled with the human translation directions. We inspect two critical factors, the train-test direction match (whether the human translation directions in the training and test sets are aligned), and data-model direction match (whether the model learns in the same direction as the human translation direction in the dataset). We show that these two factors have a large causal effect on the MT performance, in addition to the test-model direction mismatch highlighted by existing work on the impact of translationese. In light of our findings, we provide a set of suggestions for MT training and evaluation. Our code and data are at https://github.com/EdisonNi-hku/CausalMT

Improvements in text generation technologies such as machine translation have necessitated more costly and time-consuming human evaluation procedures to ensure an accurate signal. We investigate a simple way to reduce cost by reducing the number of text segments that must be annotated in order to accurately predict a score for a complete test set. Using a sampling approach, we demonstrate that information from document membership and automatic metrics can help improve estimates compared to a pure random sampling baseline. We achieve gains of up to 20% in average absolute error by leveraging stratified sampling and control variates. Our techniques can improve estimates made from a fixed annotation budget, are easy to implement, and can be applied to any problem with structure similar to the one we study.

Machine translation (MT) evaluation often focuses on accuracy and fluency, without paying much attention to translation style. This means that, even when considered accurate and fluent, MT output can still sound less natural than high quality human translations or text originally written in the target language. Machine translation output notably exhibits lower lexical diversity, and employs constructs that mirror those in the source sentence. In this work we propose a method for training MT systems to achieve a more natural style, i.e. mirroring the style of text originally written in the target language. Our method tags parallel training data according to the naturalness of the target side by contrasting language models trained on natural and translated data. Tagging data allows us to put greater emphasis on target sentences originally written in the target language. Automatic metrics show that the resulting models achieve lexical richness on par with human translations, mimicking a style much closer to sentences originally written in the target language. Furthermore, we find that their output is preferred by human experts when compared to the baseline translations.

This paper presents the results of the WMT22 Metrics Shared Task. Participants submitting automatic MT evaluation metrics were asked to score the outputs of the translation systems competing in the WMT22 News Translation Task on four different domains: news, social, ecommerce, and chat. All metrics were evaluated on how well they correlate with human ratings at the system and segment level. Similar to last year, we acquired our own human ratings based on expert-based human evaluation via Multidimensional Quality Metrics (MQM). This setup had several advantages, among other things: (i) expert-based evaluation is more reliable, (ii) we extended the pool of translations by 5 additional translations based on MBR decoding or rescoring which are challenging for current metrics. In addition, we initiated a challenge set subtask, where participants had to create contrastive test suites for evaluating metrics’ ability to capture and penalise specific types of translation errors. Finally, we present an extensive analysis on how well metrics perform on three language pairs: English to German, English to Russian and Chinese to English. The results demonstrate the superiority of neural-based learned metrics and demonstrate again that overlap metrics like Bleu, spBleu or chrf correlate poorly with human ratings. The results also reveal that neural-based metrics are remarkably robust across different domains and challenges.

We present the results from the 8th round of the WMT shared task on MT Automatic PostEditing, which consists in automatically correcting the output of a “black-box” machine translation system by learning from human corrections. This year, the task focused on a new language pair (English→Marathi) and on data coming from multiple domains (healthcare, tourism, and general/news). Although according to several indicators this round was of medium-high difficulty compared to the past,the best submission from the three participating teams managed to significantly improve (with an error reduction of 3.49 TER points) the original translations produced by a generic neural MT system.

In Neural Machine Translation, it is typically assumed that the sentence with the highest estimated probability should also be the translation with the highest quality as measured by humans. In this work, we question this assumption and show that model estimates and translation quality only vaguely correlate. We apply Minimum Bayes Risk (MBR) decoding on unbiased samples to optimize diverse automated metrics of translation quality as an alternative inference strategy to beam search. Instead of targeting the hypotheses with the highest model probability, MBR decoding extracts the hypotheses with the highest estimated quality. Our experiments show that the combination of a neural translation model with a neural reference-based metric, Bleurt, results in significant improvement in human evaluations. This improvement is obtained with translations different from classical beam-search output: These translations have much lower model likelihood and are less favored by surface metrics like Bleu.

Human evaluation of modern high-quality machine translation systems is a difficult problem, and there is increasing evidence that inadequate evaluation procedures can lead to erroneous conclusions. While there has been considerable research on human evaluation, the field still lacks a commonly accepted standard procedure. As a step toward this goal, we propose an evaluation methodology grounded in explicit error analysis, based on the Multidimensional Quality Metrics (MQM) framework. We carry out the largest MQM research study to date, scoring the outputs of top systems from the WMT 2020 shared task in two language pairs using annotations provided by professional translators with access to full document context. We analyze the resulting data extensively, finding among other results a substantially different ranking of evaluated systems from the one established by the WMT crowd workers, exhibiting a clear preference for human over machine output. Surprisingly, we also find that automatic metrics based on pre-trained embeddings can outperform human crowd workers. We make our corpus publicly available for further research.

Reference-free evaluation has the potential to make machine translation evaluation substantially more scalable, allowing us to pivot easily to new languages or domains. It has been recently shown that the probabilities given by a large, multilingual model can achieve state of the art results when used as a reference-free metric. We experiment with various modifications to this model, and demonstrate that by scaling it up we can match the performance of BLEU. We analyze various potential weaknesses of the approach, and find that it is surprisingly robust and likely to offer reasonable performance across a broad spectrum of domains and different system qualities.

This paper presents the results of the newstranslation task, the multilingual low-resourcetranslation for Indo-European languages, thetriangular translation task, and the automaticpost-editing task organised as part of the Con-ference on Machine Translation (WMT) 2021.In the news task, participants were asked tobuild machine translation systems for any of10 language pairs, to be evaluated on test setsconsisting mainly of news stories. The taskwas also opened up to additional test suites toprobe specific aspects of translation.

This paper presents the results of the WMT21 Metrics Shared Task. Participants were asked to score the outputs of the translation systems competing in the WMT21 News Translation Task with automatic metrics on two different domains: news and TED talks. All metrics were evaluated on how well they correlate at the system- and segment-level with human ratings. Contrary to previous years’ editions, this year we acquired our own human ratings based on expert-based human evaluation via Multidimensional Quality Metrics (MQM). This setup had several advantages: (i) expert-based evaluation has been shown to be more reliable, (ii) we were able to evaluate all metrics on two different domains using translations of the same MT systems, (iii) we added 5 additional translations coming from the same system during system development. In addition, we designed three challenge sets that evaluate the robustness of all automatic metrics. We present an extensive analysis on how well metrics perform on three language pairs: English to German, English to Russian and Chinese to English. We further show the impact of different reference translations on reference-based metrics and compare our expert-based MQM annotation with the DA scores acquired by WMT.

Multilingual Neural Machine Translation (MNMT) models are commonly trained on a joint set of bilingual corpora which is acutely English-centric (i.e. English either as source or target language). While direct data between two languages that are non-English is explicitly available at times, its use is not common. In this paper, we first take a step back and look at the commonly used bilingual corpora (WMT), and resurface the existence and importance of implicit structure that existed in it: multi-way alignment across examples (the same sentence in more than two languages). We set out to study the use of multi-way aligned examples in order to enrich the original English-centric parallel corpora. We reintroduce this direct parallel data from multi-way aligned corpora between all source and target languages. By doing so, the English-centric graph expands into a complete graph, every language pair being connected. We call MNMT with such connectivity pattern complete Multilingual Neural Machine Translation (cMNMT) and demonstrate its utility and efficacy with a series of experiments and analysis. In combination with a novel training data sampling strategy that is conditioned on the target language only, cMNMT yields competitive translation quality for all language pairs. We further study the size effect of multi-way aligned data, its transfer learning capabilities and how it eases adding a new language in MNMT. Finally, we stress test cMNMT at scale and demonstrate that we can train a cMNMT model with up to 12,432 language pairs that provides competitive translation quality for all language pairs.

We present the results of the 6th round of the WMT task on MT Automatic Post-Editing. The task consists in automatically correcting the output of a “black-box” machine translation system by learning from existing human corrections of different sentences. This year, the challenge consisted of fixing the errors present in English Wikipedia pages translated into German and Chinese by state-ofthe-art, not domain-adapted neural MT (NMT) systems unknown to participants. Six teams participated in the English-German task, submitting a total of 11 runs. Two teams participated in the English-Chinese task submitting 2 runs each. Due to i) the different source/domain of data compared to the past (Wikipedia vs Information Technology), ii) the different quality of the initial translations to be corrected and iii) the introduction of a new language pair (English-Chinese), this year’s results are not directly comparable with last year’s round. However, on both language directions, participants’ submissions show considerable improvements over the baseline results. On English-German, the top ranked system improves over the baseline by -11.35 TER and +16.68 BLEU points, while on EnglishChinese the improvements are respectively up to -12.13 TER and +14.57 BLEU points. Overall, coherent gains are also highlighted by the outcomes of human evaluation, which confirms the effectiveness of APE to improve MT quality, especially in the new generic domain selected for this year’s round.

This paper presents the results of the WMT20 Metrics Shared Task. Participants were asked to score the outputs of the translation systems competing in the WMT20 News Translation Task with automatic metrics. Ten research groups submitted 27 metrics, four of which are reference-less “metrics”. In addition, we computed five baseline metrics, including sentBLEU, BLEU, TER and using the SacreBLEU scorer. All metrics were evaluated on how well they correlate at the system-, document- and segment-level with the WMT20 official human scores. We present an extensive analysis on influence of different reference translations on metric reliability, how well automatic metrics score human translations, and we also flag major discrepancies between metric and human scores when evaluating MT systems. Finally, we investigate whether we can use automatic metrics to flag incorrect human ratings.

The quality of machine translation systems has dramatically improved over the last decade, and as a result, evaluation has become an increasingly challenging problem. This paper describes our contribution to the WMT 2020 Metrics Shared Task, the main benchmark for automatic evaluation of translation. We make several submissions based on BLEURT, a previously published which uses transfer learning. We extend the metric beyond English and evaluate it on 14 language pairs for which fine-tuning data is available, as well as 4 “zero-shot” language pairs, for which we have no labelled examples. Additionally, we focus on English to German and demonstrate how to combine BLEURT’s predictions with those of YiSi and use alternative reference translations to enhance the performance. Empirical results show that the models achieve competitive results on the WMT Metrics 2019 Shared Task, indicating their promise for the 2020 edition.

Automatic evaluation comparing candidate translations to human-generated paraphrases of reference translations has recently been proposed by freitag2020bleu. When used in place of original references, the paraphrased versions produce metric scores that correlate better with human judgment. This effect holds for a variety of different automatic metrics, and tends to favor natural formulations over more literal (translationese) ones. In this paper we compare the results of performing end-to-end system development using standard and paraphrased references. With state-of-the-art English-German NMT components, we show that tuning to paraphrased references produces a system that is ignificantly better according to human judgment, but 5 BLEU points worse when tested on standard references. Our work confirms the finding that paraphrased references yield metric scores that correlate better with human judgment, and demonstrates for the first time that using these scores for system development can lead to significant improvements.

Machine translation has an undesirable propensity to produce “translationese” artifacts, which can lead to higher BLEU scores while being liked less by human raters. Motivated by this, we model translationese and original (i.e. natural) text as separate languages in a multilingual model, and pose the question: can we perform zero-shot translation between original source text and original target text? There is no data with original source and original target, so we train a sentence-level classifier to distinguish translationese from original target text, and use this classifier to tag the training data for an NMT model. Using this technique we bias the model to produce more natural outputs at test time, yielding gains in human evaluation scores on both accuracy and fluency. Additionally, we demonstrate that it is possible to bias the model to produce translationese and game the BLEU score, increasing it while decreasing human-rated quality. We analyze these outputs using metrics measuring the degree of translationese, and present an analysis of the volatility of heuristic-based train-data tagging.

We propose a simple and effective method for machine translation evaluation which does not require reference translations. Our approach is based on (1) grounding the entity mentions found in each source sentence and candidate translation against a large-scale multilingual knowledge base, and (2) measuring the recall of the grounded entities found in the candidate vs. those found in the source. Our approach achieves the highest correlation with human judgements on 9 out of the 18 language pairs from the WMT19 benchmark for evaluation without references, which is the largest number of wins for a single evaluation method on this task. On 4 language pairs, we also achieve higher correlation with human judgements than BLEU. To foster further research, we release a dataset containing 1.8 million grounded entity mentions across 18 language pairs from the WMT19 metrics track data.

The quality of automatic metrics for machine translation has been increasingly called into question, especially for high-quality systems. This paper demonstrates that, while choice of metric is important, the nature of the references is also critical. We study different methods to collect references and compare their value in automated evaluation by reporting correlation with human evaluation for a variety of systems and metrics. Motivated by the finding that typical references exhibit poor diversity, concentrating around translationese language, we develop a paraphrasing task for linguists to perform on existing reference translations, which counteracts this bias. Our method yields higher correlation with human judgment not only for the submissions of WMT 2019 English to German, but also for Back-translation and APE augmented MT output, which have been shown to have low correlation with automatic metrics using standard references. We demonstrate that our methodology improves correlation with all modern evaluation metrics we look at, including embedding-based methods. To complete this picture, we reveal that multi-reference BLEU does not improve the correlation for high quality output, and present an alternative multi-reference formulation that is more effective.

In this work, we train an Automatic Post-Editing (APE) model and use it to reveal biases in standard MT evaluation procedures. The goal of our APE model is to correct typical errors introduced by the translation process, and convert the “translationese” output into natural text. Our APE model is trained entirely on monolingual data that has been round-trip translated through English, to mimic errors that are similar to the ones introduced by NMT. We apply our model to the output of existing NMT systems, and demonstrate that, while the human-judged quality improves in all cases, BLEU scores drop with forward-translated test sets. We verify these results for the WMT18 English to German, WMT15 English to French, and WMT16 English to Romanian tasks. Furthermore, we selectively apply our APE model on the output of the top submissions of the most recent WMT evaluation campaigns. We see quality improvements on all tasks of up to 2.5 BLEU points.

Generating text from structured data is important for various tasks such as question answering and dialog systems. We show that in at least one domain, without any supervision and only based on unlabeled text, we are able to build a Natural Language Generation (NLG) system with higher performance than supervised approaches. In our approach, we interpret the structured data as a corrupt representation of the desired output and use a denoising auto-encoder to reconstruct the sentence. We show how to introduce noise into training examples that do not contain structured data, and that the resulting denoising auto-encoder generalizes to generate correct sentences when given structured data.

The basic concept in Neural Machine Translation (NMT) is to train a large Neural Network that maximizes the translation performance on a given parallel corpus. NMT is then using a simple left-to-right beam-search decoder to generate new translations that approximately maximize the trained conditional probability. The current beam search strategy generates the target sentence word by word from left-to-right while keeping a fixed amount of active candidates at each time step. First, this simple search is less adaptive as it also expands candidates whose scores are much worse than the current best. Secondly, it does not expand hypotheses if they are not within the best scoring candidates, even if their scores are close to the best one. The latter one can be avoided by increasing the beam size until no performance improvement can be observed. While you can reach better performance, this has the drawback of a slower decoding speed. In this paper, we concentrate on speeding up the decoder by applying a more flexible beam search strategy whose candidate size may vary at each time step depending on the candidate scores. We speed up the original decoder by up to 43% for the two language pairs German to English and Chinese to English without losing any translation quality.

EU-BRIDGE is a European research project which is aimed at developing innovative speech translation technology. One of the collaborative efforts within EU-BRIDGE is to produce joint submissions of up to four different partners to the evaluation campaign at the 2014 International Workshop on Spoken Language Translation (IWSLT). We submitted combined translations to the German→English spoken language translation (SLT) track as well as to the German→English, English→German and English→French machine translation (MT) tracks. In this paper, we present the techniques which were applied by the different individual translation systems of RWTH Aachen University, the University of Edinburgh, Karlsruhe Institute of Technology, and Fondazione Bruno Kessler. We then show the combination approach developed at RWTH Aachen University which combined the individual systems. The consensus translations yield empirical gains of up to 2.3 points in BLEU and 1.2 points in TER compared to the best individual system.

Punctuation prediction is an important task in spoken language translation and can be performed by using a monolingual phrase-based translation system to translate from unpunctuated to text with punctuation. However, a punctuation prediction system based on phrase-based translation is not able to capture long-range dependencies between words and punctuation marks. In this paper, we propose to employ hierarchical translation in place of phrase-based translation and show that this approach is more robust for unseen word sequences. Furthermore, we analyze different optimization criteria for tuning the scaling factors of a monolingual statistical machine translation system. In our experiments, we compare the new approach with other punctuation prediction methods and show improvements in terms of F1-Score and BLEU on the IWSLT 2014 German→English and English→French translation tasks.

This work describes the statistical machine translation (SMT) systems of RWTH Aachen University developed for the evaluation campaign International Workshop on Spoken Language Translation (IWSLT) 2013. We participated in the English→French, English↔German, Arabic→English, Chinese→English and Slovenian↔English MT tracks and the English→French and English→German SLT tracks. We apply phrase-based and hierarchical SMT decoders, which are augmented by state-of-the-art extensions. The novel techniques we experimentally evaluate include discriminative phrase training, a continuous space language model, a hierarchical reordering model, a word class language model, domain adaptation via data selection and system combination of standard and reverse order models. By application of these methods we can show considerable improvements over the respective baseline systems.

EU-BRIDGE1 is a European research project which is aimed at developing innovative speech translation technology. This paper describes one of the collaborative efforts within EUBRIDGE to further advance the state of the art in machine translation between two European language pairs, English→French and German→English. Four research institutions involved in the EU-BRIDGE project combined their individual machine translation systems and participated with a joint setup in the machine translation track of the evaluation campaign at the 2013 International Workshop on Spoken Language Translation (IWSLT). We present the methods and techniques to achieve high translation quality for text translation of talks which are applied at RWTH Aachen University, the University of Edinburgh, Karlsruhe Institute of Technology, and Fondazione Bruno Kessler. We then show how we have been able to considerably boost translation performance (as measured in terms of the metrics BLEU and TER) by means of system combination. The joint setups yield empirical gains of up to 1.4 points in BLEU and 2.8 points in TER on the IWSLT test sets compared to the best single systems.

In this paper, the automatic speech recognition (ASR) and statistical machine translation (SMT) systems of RWTH Aachen University developed for the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2012 are presented. We participated in the ASR (English), MT (English-French, Arabic-English, Chinese-English, German-English) and SLT (English-French) tracks. For the MT track both hierarchical and phrase-based SMT decoders are applied. A number of different techniques are evaluated in the MT and SLT tracks, including domain adaptation via data selection, translation model interpolation, phrase training for hierarchical and phrase-based systems, additional reordering model, word class language model, various Arabic and Chinese segmentation methods, postprocessing of speech recognition output with an SMT system, and system combination. By application of these methods we can show considerable improvements over the respective baseline systems.

In this paper the statistical machine translation (SMT) systems of RWTH Aachen University developed for the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2011 is presented. We participated in the MT (English-French, Arabic-English, ChineseEnglish) and SLT (English-French) tracks. Both hierarchical and phrase-based SMT decoders are applied. A number of different techniques are evaluated, including domain adaptation via monolingual and bilingual data selection, phrase training, different lexical smoothing methods, additional reordering models for the hierarchical system, various Arabic and Chinese segmentation methods, punctuation prediction for speech recognition output, and system combination. By application of these methods we can show considerable improvements over the respective baseline systems.

The Quaero program is an international project promoting research and industrial innovation on technologies for automatic analysis and classification of multimedia and multilingual documents. Within the program framework, research organizations and industrial partners collaborate to develop prototypes of innovating applications and services for access and usage of multimedia data. One of the topics addressed is the translation of spoken language. Each year, a project-internal evaluation is conducted by DGA to monitor the technological advances. This work describes the design and results of the 2011 evaluation campaign. The participating partners were RWTH, KIT, LIMSI and SYSTRAN. Their approaches are compared on both ASR output and reference transcripts of speech data for the translation between French and German. The results show that the developed techniques further the state of the art and improve translation quality.

Punctuation prediction is an important task in Spoken Language Translation. The output of speech recognition systems does not typically contain punctuation marks. In this paper we analyze different methods for punctuation prediction and show improvements in the quality of the final translation output. In our experiments we compare the different approaches and show improvements of up to 0.8 BLEU points on the IWSLT 2011 English French Speech Translation of Talks task using a translation system to translate from unpunctuated to punctuated text instead of a language model based punctuation prediction method. Furthermore, we do a system combination of the hypotheses of all our different approaches and get an additional improvement of 0.4 points in BLEU.