Markus Freitag

Patrick Fernandes, Daniel Deutsch, Mara Finkelstein et al. · deepmind

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.

Wenda Xu, Daniel Deutsch, Mara Finkelstein et al. · cmu

Recent large language models (LLM) are leveraging human feedback to improve their generation quality. However, human feedback is costly to obtain, especially during inference. In this work, we propose LLMRefine, an inference time optimization method to refine LLM's output. The core idea is to use a learned fine-grained feedback model to pinpoint defects and guide LLM to refine them iteratively. Using original LLM as a proposal of edits, LLMRefine searches for defect-less text via simulated annealing, trading off the exploration and exploitation. We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization. LLMRefine consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.

Tom Kocmi, Eleftherios Avramidis, Rachel Bawden et al. · eth-zurich, microsoft-research

This is the preliminary ranking of WMT24 General MT systems based on automatic metrics. The official ranking will be a human evaluation, which is superior to the automatic ranking and supersedes it. The purpose of this report is not to interpret any findings but only provide preliminary results to the participants of the General MT task that may be useful during the writing of the system submission.

Eleftheria Briakou, Jiaming Luo, Colin Cherry et al.

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 WMT2024.

Daniel Deutsch, Juraj Juraska, Mara Finkelstein et al.

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.

Daniel Deutsch, Eleftheria Briakou, Isaac Caswell et al.

As large language models (LLM) become more and more capable in languages other than English, it is important to collect benchmark datasets in order to evaluate their multilingual performance, including on tasks like machine translation (MT). In this work, we extend the WMT24 dataset to cover 55 languages by collecting new human-written references and post-edits for 46 new languages and dialects in addition to post-edits of the references in 8 out of 9 languages in the original WMT24 dataset. The dataset covers four domains: literary, news, social, and speech. We benchmark a variety of MT providers and LLMs on the collected dataset using automatic metrics and find that LLMs are the best-performing MT systems in all 55 languages. These results should be confirmed using a human-based evaluation, which we leave for future work.

Gergely Flamich, David Vilar, Jan-Thorsten Peter et al.

The goal of translation, be it by human or by machine, is, given some text in a source language, to produce text in a target language that simultaneously 1) preserves the meaning of the source text and 2) achieves natural expression in the target language. However, researchers in the machine translation community usually assess translations using a single score intended to capture semantic accuracy and the naturalness of the output simultaneously. In this paper, we build on recent advances in information theory to mathematically prove and empirically demonstrate that such single-score summaries do not and cannot give the complete picture of a system's true performance. Concretely, we prove that a tradeoff exists between accuracy and naturalness and demonstrate it by evaluating the submissions to the WMT24 shared task. Our findings help explain well-known empirical phenomena, such as the observation that optimizing translation systems for a specific accuracy metric (like BLEU) initially improves the system's naturalness, while ``overfitting'' the system to the metric can significantly degrade its naturalness. Thus, we advocate for a change in how translations are evaluated: rather than comparing systems using a single number, they should be compared on an accuracy-naturalness plane.

Muhammed Yusuf Kocyigit, Eleftheria Briakou, Daniel Deutsch et al. · mit

Data contamination -- the accidental consumption of evaluation examples within the pre-training data -- can undermine the validity of evaluation benchmarks. In this paper, we present a rigorous analysis of the effects of contamination on language models at 1B and 8B scales on the machine translation task. Starting from a carefully decontaminated train-test split, we systematically introduce contamination at various stages, scales, and data formats to isolate its effect and measure its impact on performance metrics. Our experiments reveal that contamination with both source and target substantially inflates BLEU scores, and this inflation is 2.5 times larger (up to 30 BLEU points) for 8B compared to 1B models. In contrast, source-only and target-only contamination generally produce smaller, less consistent over-estimations. Finally, we study how the temporal distribution and frequency of contaminated samples influence performance over-estimation across languages with varying degrees of data resources.

Mara Finkelstein, Dan Deutsch, Parker Riley et al.

As LLMs continue to become more powerful and versatile, human evaluation has quickly become intractable at scale and reliance on automatic metrics has become the norm. Recently, it has been shown that LLMs are themselves state-of-the-art evaluators for many tasks. These Autoraters are typically designed so that they generalize to new systems and test sets. In practice, however, evaluation is performed on a small set of fixed, canonical test sets, which are carefully curated to measure certain capabilities of interest and are not changed frequently. In this work, we design a method which specializes a prompted Autorater to a given test set, by leveraging historical ratings on the test set to construct in-context learning (ICL) examples. We evaluate our Specialist method on the task of fine-grained machine translation evaluation, and show that it dramatically outperforms the state-of-the-art XCOMET metric by 54% and 119% on the WMT'23 and WMT'24 test sets, respectively. We perform extensive analyses to understand the representations learned by our Specialist metrics, and how variability in rater behavior affects their performance. We also verify the generalizability and robustness of our Specialist method for designing automatic metrics across different numbers of ICL examples, LLM backbones, systems to evaluate, and evaluation tasks.

Lily H. Zhang, Hamid Dadkhahi, Mara Finkelstein et al. · mit

Despite growing interest in incorporating feedback to improve language models, most efforts focus only on sequence-level annotations. In this work, we explore the potential of utilizing fine-grained span-level annotations from offline datasets to improve model quality. We develop a simple finetuning algorithm, called Training with Annotations (TWA), to directly train machine translation models on such annotated data. TWA utilizes targeted span-level error information while also flexibly learning what to penalize within a span. Moreover, TWA considers the overall trajectory of a sequence when deciding which non-error spans to utilize as positive signals. Experiments on English-German and Chinese-English machine translation show that TWA outperforms baselines such as Supervised FineTuning on sequences filtered for quality and Direct Preference Optimization on pairs constructed from the same data.

Tom Kocmi, Eleftherios Avramidis, Rachel Bawden et al. · eth-zurich, microsoft-research

We present the preliminary rankings of machine translation (MT) systems submitted to the WMT25 General Machine Translation Shared Task, as determined by automatic evaluation metrics. Because these rankings are derived from automatic evaluation, they may exhibit a bias toward systems that employ re-ranking techniques, such as Quality Estimation or Minimum Bayes Risk decoding. The official WMT25 ranking will be based on human evaluation, which is more reliable and will supersede these results. The official WMT25 ranking will be based on human evaluation, which is more reliable and will supersede these results. The purpose of releasing these findings now is to assist task participants with their system description papers; not to provide final findings.

Firas Trabelsi, David Vilar, Mara Finkelstein et al.

Minimum Bayes Risk (MBR) decoding is a powerful decoding strategy widely used for text generation tasks, but its quadratic computational complexity limits its practical application. This paper presents a novel approach for approximating MBR decoding using matrix completion techniques, focusing on the task of machine translation. We formulate MBR decoding as a matrix completion problem, where the utility metric scores between candidate hypotheses and pseudo-reference translations form a low-rank matrix. First, we empirically show that the scores matrices indeed have a low-rank structure. Then, we exploit this by only computing a random subset of the scores and efficiently recover the missing entries in the matrix by applying the Alternating Least Squares (ALS) algorithm, thereby enabling a fast approximation of the MBR decoding process. Our experimental results on machine translation tasks demonstrate that the proposed method requires 1/16 utility metric computations compared to vanilla MBR decoding while achieving equal translation quality measured by COMET22 on the WMT22 dataset (en<>de and en<>ru). We also benchmark our method against other approximation methods and we show gains in quality when comparing to them.

Wenda Xu, Danqing Wang, Liangming Pan et al.

Automatically evaluating the quality of language generation is critical. Although recent learned metrics show high correlation with human judgement, these metrics can not explain their verdict or associate the scores with defects in generated text. To address this limitation, we present InstructScore, an 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.

Rohan Anil, Andrew M. Dai, Orhan Firat et al.

We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 is a Transformer-based model trained using a mixture of objectives. Through extensive evaluations on English and multilingual language, and reasoning tasks, we demonstrate that PaLM 2 has significantly improved quality on downstream tasks across different model sizes, while simultaneously exhibiting faster and more efficient inference compared to PaLM. This improved efficiency enables broader deployment while also allowing the model to respond faster, for a more natural pace of interaction. PaLM 2 demonstrates robust reasoning capabilities exemplified by large improvements over PaLM on BIG-Bench and other reasoning tasks. PaLM 2 exhibits stable performance on a suite of responsible AI evaluations, and enables inference-time control over toxicity without additional overhead or impact on other capabilities. Overall, PaLM 2 achieves state-of-the-art performance across a diverse set of tasks and capabilities. When discussing the PaLM 2 family, it is important to distinguish between pre-trained models (of various sizes), fine-tuned variants of these models, and the user-facing products that use these models. In particular, user-facing products typically include additional pre- and post-processing steps. Additionally, the underlying models may evolve over time. Therefore, one should not expect the performance of user-facing products to exactly match the results reported in this report.

Behrooz Ghorbani, Orhan Firat, Markus Freitag et al.

We present an empirical study of scaling properties of encoder-decoder Transformer models used in neural machine translation (NMT). We show that cross-entropy loss as a function of model size follows a certain scaling law. Specifically (i) We propose a formula which describes the scaling behavior of cross-entropy loss as a bivariate function of encoder and decoder size, and show that it gives accurate predictions under a variety of scaling approaches and languages; we show that the total number of parameters alone is not sufficient for such purposes. (ii) We observe different power law exponents when scaling the decoder vs scaling the encoder, and provide recommendations for optimal allocation of encoder/decoder capacity based on this observation. (iii) We also report that the scaling behavior of the model is acutely influenced by composition bias of the train/test sets, which we define as any deviation from naturally generated text (either via machine generated or human translated text). We observe that natural text on the target side enjoys scaling, which manifests as successful reduction of the cross-entropy loss. (iv) Finally, we investigate the relationship between the cross-entropy loss and the quality of the generated translations. We find two different behaviors, depending on the nature of the test data. For test sets which were originally translated from target language to source language, both loss and BLEU score improve as model size increases. In contrast, for test sets originally translated from source language to target language, the loss improves, but the BLEU score stops improving after a certain threshold. We release generated text from all models used in this study.

Scott Roy, Cliff Brunk, Kyu-Young Kim et al.

One of the challenges in a task oriented natural language application like the Google Assistant, Siri, or Alexa is to localize the output to many languages. This paper explores doing this by applying machine translation to the English output. Using machine translation is very scalable, as it can work with any English output and can handle dynamic text, but otherwise the problem is a poor fit. The required quality bar is close to perfection, the range of sentences is extremely narrow, and the sentences are often very different than the ones in the machine translation training data. This combination of requirements is novel in the field of domain adaptation for machine translation. We are able to reach the required quality bar by building on existing ideas and adding new ones: finetuning on in-domain translations, adding sentences from the Web, adding semantic annotations, and using automatic error detection. The paper shares our approach and results, together with a distillation model to serve the translation models at scale.

Markus Freitag, George Foster, David Grangier et al.

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.

Sweta Agrawal, George Foster, Markus Freitag et al.

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.

Markus Freitag, George Foster, David Grangier et al.

Automatic evaluation comparing candidate translations to human-generated paraphrases of reference translations has recently been proposed by Freitag et al. 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 significantly 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.

Markus Freitag, Orhan Firat

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 the 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 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 111*112=12,432 language pairs that provides competitive translation quality for all language pairs.

Thibault Sellam, Amy Pu, Hyung Won Chung et al.

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 metric based on 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.

Zorik Gekhman, Roee Aharoni, Genady Beryozkin et al.

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.

Markus Freitag, David Grangier, Isaac Caswell

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.

Parker Riley, Isaac Caswell, Markus Freitag et al.

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 sentence-level classifiers 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 models using metrics to measure the degree of translationese in the output, and present an analysis of the capriciousness of heuristically-based train-data tagging.

Markus Freitag, Isaac Caswell, Scott Roy

In this work, we train an Automatic Post-Editing (APE) model and use it to reveal biases in standard Machine Translation (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.

Markus Freitag, Scott Roy

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.

Baskaran Sankaran, Markus Freitag, Yaser Al-Onaizan

Neural Machine Translation (NMT) models usually use large target vocabulary sizes to capture most of the words in the target language. The vocabulary size is a big factor when decoding new sentences as the final softmax layer normalizes over all possible target words. To address this problem, it is widely common to restrict the target vocabulary with candidate lists based on the source sentence. Usually, the candidate lists are a combination of external word-to-word aligner, phrase table entries or most frequent words. In this work, we propose a simple and yet novel approach to learn candidate lists directly from the attention layer during NMT training. The candidate lists are highly optimized for the current NMT model and do not need any external computation of the candidate pool. We show significant decoding speedup compared with using the entire vocabulary, without losing any translation quality for two language pairs.

Markus Freitag, Yaser Al-Onaizan, Baskaran Sankaran

Knowledge distillation describes a method for training a student network to perform better by learning from a stronger teacher network. Translating a sentence with an Neural Machine Translation (NMT) engine is time expensive and having a smaller model speeds up this process. We demonstrate how to transfer the translation quality of an ensemble and an oracle BLEU teacher network into a single NMT system. Further, we present translation improvements from a teacher network that has the same architecture and dimensions of the student network. As the training of the student model is still expensive, we introduce a data filtering method based on the knowledge of the teacher model that not only speeds up the training, but also leads to better translation quality. Our techniques need no code change and can be easily reproduced with any NMT architecture to speed up the decoding process.

Markus Freitag, Yaser Al-Onaizan

Neural Machine Translation (NMT) is a new approach for automatic translation of text from one human language into another. The basic concept in NMT is to train a large Neural Network that maximizes the translation performance on a given parallel corpus. NMT is gaining popularity in the research community because it outperformed traditional SMT approaches in several translation tasks at WMT and other evaluation tasks/benchmarks at least for some language pairs. However, many of the enhancements in SMT over the years have not been incorporated into the NMT framework. In this paper, we focus on one such enhancement namely domain adaptation. We propose an approach for adapting a NMT system to a new domain. The main idea behind domain adaptation is that the availability of large out-of-domain training data and a small in-domain training data. We report significant gains with our proposed method in both automatic metrics and a human subjective evaluation metric on two language pairs. With our adaptation method, we show large improvement on the new domain while the performance of our general domain only degrades slightly. In addition, our approach is fast enough to adapt an already trained system to a new domain within few hours without the need to retrain the NMT model on the combined data which usually takes several days/weeks depending on the volume of the data.