This paper describes our submissions to the 2023 Conference on Machine Translation (WMT-23) Metrics shared task. Knowledge distillation is commonly used to create smaller student models that mimic larger teacher model while reducing the model size and hence inference cost in production. In this work, we apply knowledge distillation to machine translation evaluation metrics and distill existing reference-based teacher metrics into reference-free (quality estimation; QE) student metrics. We mainly focus on students of Unbabel’s COMET22 reference-based metric. When evaluating on the official WMT-22 Metrics evaluation task, our distilled Cometoid QE metrics outperform all other QE metrics on that set while matching or out-performing the reference-based teacher metric. Our metrics never see the human ground-truth scores directly – only the teacher metric was trained on human scores by its original creators. We also distill ChrF sentence-level scores into a neural QE metric and find that our reference-free (and fully human-score-free) student metric ChrFoid outperforms its teacher metric by over 7% pairwise accuracy on the same WMT-22 task, rivaling other existing QE metrics.

Many machine translation toolkits make use of a data preparation step wherein raw data is transformed into a tensor format that can be used directly by the trainer. This preparation step is increasingly at odds with modern research and development practices because this process produces a static, unchangeable version of the training data, making common training-time needs difficult (e.g., subword sampling), time-consuming (preprocessing with large data can take days), expensive (e.g., disk space), and cumbersome (managing experiment combinatorics). We propose an alternative approach that separates the generation of data from the consumption of that data. In this approach, there is no separate pre-processing step; data generation produces an infinite stream of permutations of the raw training data, which the trainer tensorizes and batches as it is consumed. Additionally, this data stream can be manipulated by a set of user-definable operators that provide on-the-fly modifications, such as data normalization, augmentation or filtering. We release an open-source toolkit, SOTASTREAM, that implements this approach: https://github.com/marian-nmt/sotastream. We show that it cuts training time, adds flexibility, reduces experiment management complexity, and reduces disk space, all without affecting the accuracy of the trained models.

Neural machine translation models often contain large target vocabularies. The calculation of logits, softmax and beam search is computationally costly over so many classes. We investigate the use of locality sensitive hashing (LSH) to reduce the number of vocabulary items that must be evaluated and explore the relationship between the hashing algorithm, translation speed and quality. Compared to prior work, our LSH-based solution does not require additional augmentation via word-frequency lists or alignments. We propose a training procedure that produces models, which, when combined with our LSH inference algorithm increase translation speed by up to 87% over the baseline, while maintaining translation quality as measured by BLEU. Apart from just using BLEU, we focus on minimizing search errors compared to the full softmax, a much harsher quality criterion.

In this work, we study hallucinations in Neural Machine Translation (NMT), which lie at an extreme end on the spectrum of NMT pathologies. Firstly, we connect the phenomenon of hallucinations under source perturbation to the Long-Tail theory of Feldman, and present an empirically validated hypothesis that explains hallucinations under source perturbation. Secondly, we consider hallucinations under corpus-level noise (without any source perturbation) and demonstrate that two prominent types of natural hallucinations (detached and oscillatory outputs) could be generated and explained through specific corpus-level noise patterns. Finally, we elucidate the phenomenon of hallucination amplification in popular data-generation processes such as Backtranslation and sequence-level Knowledge Distillation. We have released the datasets and code to replicate our results.

Recent studies emphasize the need of document context in human evaluation of machine translations, but little research has been done on the impact of user interfaces on annotator productivity and the reliability of assessments. In this work, we compare human assessment data from the last two WMT evaluation campaigns collected via two different methods for document-level evaluation. Our analysis shows that a document-centric approach to evaluation where the annotator is presented with the entire document context on a screen leads to higher quality segment and document level assessments. It improves the correlation between segment and document scores and increases inter-annotator agreement for document scores but is considerably more time consuming for annotators.

We propose a novel scheme to use the Levenshtein Transformer to perform the task of word-level quality estimation. A Levenshtein Transformer is a natural fit for this task: trained to perform decoding in an iterative manner, a Levenshtein Transformer can learn to post-edit without explicit supervision. To further minimize the mismatch between the translation task and the word-level QE task, we propose a two-stage transfer learning procedure on both augmented data and human post-editing data. We also propose heuristics to construct reference labels that are compatible with subword-level finetuning and inference. Results on WMT 2020 QE shared task dataset show that our proposed method has superior data efficiency under the data-constrained setting and competitive performance under the unconstrained setting.

Automatic metrics are commonly used as the exclusive tool for declaring the superiority of one machine translation system’s quality over another. The community choice of automatic metric guides research directions and industrial developments by deciding which models are deemed better. Evaluating metrics correlations with sets of human judgements has been limited by the size of these sets. In this paper, we corroborate how reliable metrics are in contrast to human judgements on – to the best of our knowledge – the largest collection of judgements reported in the literature. Arguably, pairwise rankings of two systems are the most common evaluation tasks in research or deployment scenarios. Taking human judgement as a gold standard, we investigate which metrics have the highest accuracy in predicting translation quality rankings for such system pairs. Furthermore, we evaluate the performance of various metrics across different language pairs and domains. Lastly, we show that the sole use of BLEU impeded the development of improved models leading to bad deployment decisions. We release the collection of 2.3M sentence-level human judgements for 4380 systems for further analysis and replication of our work.

This paper presents the JHU-Microsoft joint submission for WMT 2021 quality estimation shared task. We only participate in Task 2 (post-editing effort estimation) of the shared task, focusing on the target-side word-level quality estimation. The techniques we experimented with include Levenshtein Transformer training and data augmentation with a combination of forward, backward, round-trip translation, and pseudo post-editing of the MT output. We demonstrate the competitiveness of our system compared to the widely adopted OpenKiwi-XLM baseline. Our system is also the top-ranking system on the MT MCC metric for the English-German language pair.

Considerable effort has been made to address the data sparsity problem in neural grammatical error correction. In this work, we propose a simple and surprisingly effective unsupervised synthetic error generation method based on confusion sets extracted from a spellchecker to increase the amount of training data. Synthetic data is used to pre-train a Transformer sequence-to-sequence model, which not only improves over a strong baseline trained on authentic error-annotated data, but also enables the development of a practical GEC system in a scenario where little genuine error-annotated data is available. The developed systems placed first in the BEA19 shared task, achieving 69.47 and 64.24 F_0.5 in the restricted and low-resource tracks respectively, both on the W&I+LOCNESS test set. On the popular CoNLL 2014 test set, we report state-of-the-art results of 64.16 M² for the submitted system, and 61.30 M² for the constrained system trained on the NUCLE and Lang-8 data.

This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong sentence-level baselines, trained on large-scale data created via data-filtering and noisy back-translation and find that back-translation seems to mainly help with translationese input. We explore fine-tuning techniques, deeper models and different ensembling strategies to counter these effects. Using document boundaries present in the authentic and synthetic parallel data, we create sequences of up to 1000 subword segments and train transformer translation models. We experiment with data augmentation techniques for the smaller authentic data with document-boundaries and for larger authentic data without boundaries. We further explore multi-task training for the incorporation of document-level source language monolingual data via the BERT-objective on the encoder and two-pass decoding for combinations of sentence-level and document-level systems. Based on preliminary human evaluation results, evaluators strongly prefer the document-level systems over our comparable sentence-level system. The document-level systems also seem to score higher than the human references in source-based direct assessment.

There has been an increased interest in low-resource approaches to automatic grammatical error correction. We introduce Minimally-Augmented Grammatical Error Correction (MAGEC) that does not require any error-labelled data. Our unsupervised approach is based on a simple but effective synthetic error generation method based on confusion sets from inverted spell-checkers. In low-resource settings, we outperform the current state-of-the-art results for German and Russian GEC tasks by a large margin without using any real error-annotated training data. When combined with labelled data, our method can serve as an efficient pre-training technique

This paper describes the submissions of the “Marian” team to the WNGT 2019 efficiency shared task. Taking our dominating submissions to the previous edition of the shared task as a starting point, we develop improved teacher-student training via multi-agent dual-learning and noisy backward-forward translation for Transformer-based student models. For efficient CPU-based decoding, we propose pre-packed 8-bit matrix products, improved batched decoding, cache-friendly student architectures with parameter sharing and light-weight RNN-based decoder architectures. GPU-based decoding benefits from the same architecture changes, from pervasive 16-bit inference and concurrent streams. These modifications together with profiler-based C++ code optimization allow us to push the Pareto frontier established during the 2018 edition towards 24x (CPU) and 14x (GPU) faster models at comparable or higher BLEU values. Our fastest CPU model is more than 4x faster than last year’s fastest submission at more than 3 points higher BLEU. Our fastest GPU model at 1.5 seconds translation time is slightly faster than last year’s fastest RNN-based submissions, but outperforms them by more than 4 BLEU and 10 BLEU points respectively.

This paper describes the submissions of the “Marian” team to the WNMT 2018 shared task. We investigate combinations of teacher-student training, low-precision matrix products, auto-tuning and other methods to optimize the Transformer model on GPU and CPU. By further integrating these methods with the new averaging attention networks, a recently introduced faster Transformer variant, we create a number of high-quality, high-performance models on the GPU and CPU, dominating the Pareto frontier for this shared task.

This paper describes the Microsoft submission to the WMT2018 news translation shared task. We participated in one language direction – English-German. Our system follows current best-practice and combines state-of-the-art models with new data filtering (dual conditional cross-entropy filtering) and sentence weighting methods. We trained fairly standard Transformer-big models with an updated version of Edinburgh’s training scheme for WMT2017 and experimented with different filtering schemes for Paracrawl. According to automatic metrics (BLEU) we reached the highest score for this subtask with a nearly 2 BLEU point margin over the next strongest system. Based on human evaluation we ranked first among constrained systems. We believe this is mostly caused by our data filtering/weighting regime.

This paper describes the Microsoft and University of Edinburgh submission to the Automatic Post-editing shared task at WMT2018. Based on training data and systems from the WMT2017 shared task, we re-implement our own models from the last shared task and introduce improvements based on extensive parameter sharing. Next we experiment with our implementation of dual-source transformer models and data selection for the IT domain. Our submissions decisively wins the SMT post-editing sub-task establishing the new state-of-the-art and is a very close second (or equal, 16.46 vs 16.50 TER) in the NMT sub-task. Based on the rather weak results in the NMT sub-task, we hypothesize that neural-on-neural APE might not be actually useful.

In this work we introduce dual conditional cross-entropy filtering for noisy parallel data. For each sentence pair of the noisy parallel corpus we compute cross-entropy scores according to two inverse translation models trained on clean data. We penalize divergent cross-entropies and weigh the penalty by the cross-entropy average of both models. Sorting or thresholding according to these scores results in better subsets of parallel data. We achieve higher BLEU scores with models trained on parallel data filtered only from Paracrawl than with models trained on clean WMT data. We further evaluate our method in the context of the WMT2018 shared task on parallel corpus filtering and achieve the overall highest ranking scores of the shared task, scoring top in three out of four subtasks.

In order to extract the best possible performance from asynchronous stochastic gradient descent one must increase the mini-batch size and scale the learning rate accordingly. In order to achieve further speedup we introduce a technique that delays gradient updates effectively increasing the mini-batch size. Unfortunately with the increase of mini-batch size we worsen the stale gradient problem in asynchronous stochastic gradient descent (SGD) which makes the model convergence poor. We introduce local optimizers which mitigate the stale gradient problem and together with fine tuning our momentum we are able to train a shallow machine translation system 27% faster than an optimized baseline with negligible penalty in BLEU.

Previously, neural methods in grammatical error correction (GEC) did not reach state-of-the-art results compared to phrase-based statistical machine translation (SMT) baselines. We demonstrate parallels between neural GEC and low-resource neural MT and successfully adapt several methods from low-resource MT to neural GEC. We further establish guidelines for trustable results in neural GEC and propose a set of model-independent methods for neural GEC that can be easily applied in most GEC settings. Proposed methods include adding source-side noise, domain-adaptation techniques, a GEC-specific training-objective, transfer learning with monolingual data, and ensembling of independently trained GEC models and language models. The combined effects of these methods result in better than state-of-the-art neural GEC models that outperform previously best neural GEC systems by more than 10% M² on the CoNLL-2014 benchmark and 5.9% on the JFLEG test set. Non-neural state-of-the-art systems are outperformed by more than 2% on the CoNLL-2014 benchmark and by 4% on JFLEG.

We combine two of the most popular approaches to automated Grammatical Error Correction (GEC): GEC based on Statistical Machine Translation (SMT) and GEC based on Neural Machine Translation (NMT). The hybrid system achieves new state-of-the-art results on the CoNLL-2014 and JFLEG benchmarks. This GEC system preserves the accuracy of SMT output and, at the same time, generates more fluent sentences as it typical for NMT. Our analysis shows that the created systems are closer to reaching human-level performance than any other GEC system reported so far.

We present Marian, an efficient and self-contained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs. Marian is written entirely in C++. We describe the design of the encoder-decoder framework and demonstrate that a research-friendly toolkit can achieve high training and translation speed.

In this work, we explore multiple neural architectures adapted for the task of automatic post-editing of machine translation output. We focus on neural end-to-end models that combine both inputs mt (raw MT output) and src (source language input) in a single neural architecture, modeling {mt, src} → pe directly. Apart from that, we investigate the influence of hard-attention models which seem to be well-suited for monolingual tasks, as well as combinations of both ideas. We report results on data sets provided during the WMT-2016 shared task on automatic post-editing and can demonstrate that dual-attention models that incorporate all available data in the APE scenario in a single model improve on the best shared task system and on all other published results after the shared task. Dual-attention models that are combined with hard attention remain competitive despite applying fewer changes to the input.

We present Nematus, a toolkit for Neural Machine Translation. The toolkit prioritizes high translation accuracy, usability, and extensibility. Nematus has been used to build top-performing submissions to shared translation tasks at WMT and IWSLT, and has been used to train systems for production environments.

We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring. The platform contains a rich suite of low-level and high-level natural language processing technologies: automatic speech recognition of broadcast media, machine translation, automated tagging and classification of named entities, semantic parsing to detect relationships between entities, and automatic construction / augmentation of factual knowledge bases. Implemented on the Docker platform, it can easily be deployed, customised, and scaled to large volumes of incoming media streams.

Translation quality estimation is a task of growing importance in NLP, due to its potential to reduce post-editing human effort in disruptive ways. However, this potential is currently limited by the relatively low accuracy of existing systems. In this paper, we achieve remarkable improvements by exploiting synergies between the related tasks of word-level quality estimation and automatic post-editing. First, we stack a new, carefully engineered, neural model into a rich feature-based word-level quality estimation system. Then, we use the output of an automatic post-editing system as an extra feature, obtaining striking results on WMT16: a word-level FMULT1 score of 57.47% (an absolute gain of +7.95% over the current state of the art), and a Pearson correlation score of 65.56% for sentence-level HTER prediction (an absolute gain of +13.36%).

The utilization of statistical machine translation (SMT) has grown enormously over the last decade, many using open-source software developed by the NLP community. As commercial use has increased, there is need for software that is optimized for commercial requirements, in particular, fast phrase-based decoding and more efficient utilization of modern multicore servers. In this paper we re-examine the major components of phrase-based decoding and decoder implementation with particular emphasis on speed and scalability on multicore machines. The result is a drop-in replacement for the Moses decoder which is up to fifteen times faster and scales monotonically with the number of cores.

In this paper we provide the largest published comparison of translation quality for phrase-based SMT and neural machine translation across 30 translation directions. For ten directions we also include hierarchical phrase-based MT. Experiments are performed for the recently published United Nations Parallel Corpus v1.0 and its large six-way sentence-aligned subcorpus. In the second part of the paper we investigate aspects of translation speed, introducing AmuNMT, our efficient neural machine translation decoder. We demonstrate that current neural machine translation could already be used for in-production systems when comparing words-persecond ratios.

This paper describes the submission of the University of Edinburgh team to the IWSLT MT task for TED talks. We took part in four translation directions, en-de, de-en, en-fr, and fr-en. The models have been trained with an attentional encoder-decoder model using Nematus, training data filtering and back-translation have been applied for domain-adaptation purposes.

This paper describes the creation process and statistics of the official United Nations Parallel Corpus, the first parallel corpus composed from United Nations documents published by the original data creator. The parallel corpus presented consists of manually translated UN documents from the last 25 years (1990 to 2014) for the six official UN languages, Arabic, Chinese, English, French, Russian, and Spanish. The corpus is freely available for download under a liberal license. Apart from the pairwise aligned documents, a fully aligned subcorpus for the six official UN languages is distributed. We provide baseline BLEU scores of our Moses-based SMT systems trained with the full data of language pairs involving English and for all possible translation directions of the six-way subcorpus.