Roman Grundkiewicz

Bio: Roman Grundkiewicz is an academic researcher from Microsoft. The author has contributed to research in topics: Machine translation & Task (project management). The author has an hindex of 21, co-authored 47 publications receiving 1658 citations. Previous affiliations of Roman Grundkiewicz include Adam Mickiewicz University in Poznań.

Marian: Fast Neural Machine Translation in C++

Abstract: 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.

Automatic Extraction of Polish Language Errors from Text Edition History

Abstract: There are no large error corpora for a number of languages, despite the fact that they have multiple applications in natural language processing. The main reason underlying this situation is a high cost of manual corpora creation. In this paper we present the methods of automatic extraction of various kinds of errors such as spelling, typographical, grammatical, syntactic, semantic, and stylistic ones from text edition histories. By applying of these methods to the Wikipedia’s article revision history, we created the large and publicly available corpus of naturally-occurring language errors for Polish, called PlEWi. Finally, we analyse and evaluate the detected error categories in our corpus.

Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data

Abstract: 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 F0.5 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.

Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task

Abstract: 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.

Marian: Fast Neural Machine Translation in C++

Abstract: 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.

fairseq: A Fast, Extensible Toolkit for Sequence Modeling.

Abstract: fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. The toolkit is based on PyTorch and supports distributed training across multiple GPUs and machines. We also support fast mixed-precision training and inference on modern GPUs. A demo video can be found at this https URL

Findings of the 2016 Conference on Machine Translation

Abstract: This paper presents the results of the WMT16 shared tasks, which included five machine translation (MT) tasks (standard news, IT-domain, biomedical, multimodal, pronoun), three evaluation tasks (metrics, tuning, run-time estimation of MT quality), and an automatic post-editing task and bilingual document alignment task. This year, 102 MT systems from 24 institutions (plus 36 anonymized online systems) were submitted to the 12 translation directions in the news translation task. The IT-domain task received 31 submissions from 12 institutions in 7 directions and the Biomedical task received 15 submissions systems from 5 institutions. Evaluation was both automatic and manual (relative ranking and 100-point scale assessments). The quality estimation task had three subtasks, with a total of 14 teams, submitting 39 entries. The automatic post-editing task had a total of 6 teams, submitting 11 entries.

The CoNLL-2014 Shared Task on Grammatical Error Correction

Abstract: The CoNLL-2014 shared task was devoted to grammatical error correction of all error types. In this paper, we give the task definition, present the data sets, and describe the evaluation metric and scorer used in the shared task. We also give an overview of the various approaches adopted by the participating teams, and present the evaluation results. Compared to the CoNLL2013 shared task, we have introduced the following changes in CoNLL-2014: (1) A participating system is expected to detect and correct grammatical errors of all types, instead of just the five error types in CoNLL-2013; (2) The evaluation metric was changed from F1 to F0.5, to emphasize precision over recall; and (3) We have two human annotators who independently annotated the test essays, compared to just one human annotator in CoNLL-2013.

Findings of the 2019 Conference on Machine Translation (WMT19)

Abstract: This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2019. Participants were asked to build machine translation systems for any of 18 language pairs, to be evaluated on a test set of news stories. The main metric for this task is human judgment of translation quality. The task was also opened up to additional test suites to probe specific aspects of translation.

Findings of the 2018 Conference on Machine Translation (WMT18)

Abstract: This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2018. Participants were asked to build machine translation systems for any of 7 language pairs in both directions, to be evaluated on a test set of news stories. The main metric for this task is human judgment of translation quality. This year, we also opened up the task to additional test suites to probe specific aspects of translation.