We present SignCLIP, which re-purposes CLIP (Contrastive Language-Image Pretraining) to project spoken language text and sign language videos, two classes of natural languages of distinct modalities, into the same space. SignCLIP is an efficient method of learning useful visual representations for sign language processing from large-scale, multilingual video-text pairs, without directly optimizing for a specific task or sign language which is often of limited size.We pretrain SignCLIP on Spreadthesign, a prominent sign language dictionary consisting of ~500 thousand video clips in up to 44 sign languages, and evaluate it with various downstream datasets. SignCLIP discerns in-domain signing with notable text-to-video/video-to-text retrieval accuracy. It also performs competitively for out-of-domain downstream tasks such as isolated sign language recognition upon essential few-shot prompting or fine-tuning.We analyze the latent space formed by the spoken language text and sign language poses, which provides additional linguistic insights. Our code and models are openly available.

Automatic sign language processing is gaining popularity in Natural Language Processing (NLP) research (Yin et al., 2021). In machine translation (MT) in particular, sign language translation based on glosses is a prominent approach. In this paper, we review recent works on neural gloss translation. We find that limitations of glosses in general and limitations of specific datasets are not discussed in a transparent manner and that there is no common standard for evaluation. To address these issues, we put forward concrete recommendations for future research on gloss translation. Our suggestions advocate awareness of the inherent limitations of gloss-based approaches, realistic datasets, stronger baselines and convincing evaluation.

This paper presents work on novel machine translation (MT) systems between spoken and signed languages, where signed languages are represented in SignWriting, a sign language writing system. Our work seeks to address the lack of out-of-the-box support for signed languages in current MT systems and is based on the SignBank dataset, which contains pairs of spoken language text and SignWriting content. We introduce novel methods to parse, factorize, decode, and evaluate SignWriting, leveraging ideas from neural factored MT. In a bilingual setup—translating from American Sign Language to (American) English—our method achieves over 30 BLEU, while in two multilingual setups—translating in both directions between spoken languages and signed languages—we achieve over 20 BLEU. We find that common MT techniques used to improve spoken language translation similarly affect the performance of sign language translation. These findings validate our use of an intermediate text representation for signed languages to include them in natural language processing research.

Advancements in sign language processing have been hindered by a lack of sufficient data, impeding progress in recognition, translation, and production tasks. The absence of comprehensive sign language datasets across the world’s sign languages has widened the gap in this field, resulting in a few sign languages being studied more than others, making this research area extremely skewed mostly towards sign languages from high-income countries. In this work we introduce a new large and highly multilingual dataset for sign language translation: JWSign. The dataset consists of 2,530 hours of Bible translations in 98 sign languages, featuring more than 1,500 individual signers. On this dataset, we report neural machine translation experiments. Apart from bilingual baseline systems, we also train multilingual systems, including some that take into account the typological relatedness of signed or spoken languages. Our experiments highlight that multilingual systems are superior to bilingual baselines, and that in higher-resource scenarios, clustering language pairs that are related improves translation quality.

Sign language segmentation is a crucial task in sign language processing systems. It enables downstream tasks such as sign recognition, transcription, and machine translation. In this work, we consider two kinds of segmentation: segmentation into individual signs and segmentation into phrases, larger units comprising several signs. We propose a novel approach to jointly model these two tasks. Our method is motivated by linguistic cues observed in sign language corpora. We replace the predominant IO tagging scheme with BIO tagging to account for continuous signing. Given that prosody plays a significant role in phrase boundaries, we explore the use of optical flow features. We also provide an extensive analysis of hand shapes and 3D hand normalization. We find that introducing BIO tagging is necessary to model sign boundaries. Explicitly encoding prosody by optical flow improves segmentation in shallow models, but its contribution is negligible in deeper models. Careful tuning of the decoding algorithm atop the models further improves the segmentation quality. We demonstrate that our final models generalize to out-of-domain video content in a different signed language, even under a zero-shot setting. We observe that including optical flow and 3D hand normalization enhances the robustness of the model in this context.

Sign language translation systems are complex and require many components. As a result, it is very hard to compare methods across publications. We present an open-source implementation of a text-to-gloss-to-pose-to-video pipeline approach, demonstrating conversion from German to Swiss German Sign Language, French to French Sign Language of Switzerland, and Italian to Italian Sign Language of Switzerland. We propose three different components for the text-to-gloss translation: a lemmatizer, a rule-based word reordering and dropping component, and a neural machine translation system. Gloss-to-pose conversion occurs using data from a lexicon for three different signed languages, with skeletal poses extracted from videos. To generate a sentence, the text-to-gloss system is first run, and the pose representations of the resulting signs are stitched together.

This paper is a brief summary of the First WMT Shared Task on Sign Language Translation (WMT-SLT22), a project partly funded by EAMT. The focus of this shared task is automatic translation between signed and spoken languages. Details can be found on our website (https://www.wmt-slt.com/) or in the findings paper (Müller et al., 2022).

This paper presents the results of the Second WMT Shared Task on Sign Language Translation (WMT-SLT23; https://www.wmt-slt.com/). This shared task is concerned with automatic translation between signed and spoken languages. The task is unusual in the sense that it requires processing visual information (such as video frames or human pose estimation) beyond the well-known paradigm of text-to-text machine translation (MT). The task offers four tracks involving the following languages: Swiss German Sign Language (DSGS), French Sign Language of Switzerland (LSF-CH), Italian Sign Language of Switzerland (LIS-CH), German, French and Italian. Four teams (including one working on a baseline submission) participated in this second edition of the task, all submitting to the DSGS-to-German track. Besides a system ranking and system papers describing state-of-the-art techniques, this shared task makes the following scientific contributions: novel corpora and reproducible baseline systems. Finally, the task also resulted in publicly available sets of system outputs and more human evaluation scores for sign language translation.

This paper presents the results of the First WMT Shared Task on Sign Language Translation (WMT-SLT22).This shared task is concerned with automatic translation between signed and spoken languages. The task is novel in the sense that it requires processing visual information (such as video frames or human pose estimation) beyond the well-known paradigm of text-to-text machine translation (MT).The task featured two tracks, translating from Swiss German Sign Language (DSGS) to German and vice versa. Seven teams participated in this first edition of the task, all submitting to the DSGS-to-German track. Besides a system ranking and system papers describing state-of-the-art techniques, this shared task makes the following scientific contributions: novel corpora, reproducible baseline systems and new protocols and software for human evaluation. Finally, the task also resulted in the first publicly available set of system outputs and human evaluation scores for sign language translation.

With the success of large-scale pre-training and multilingual modeling in Natural Language Processing (NLP), recent years have seen a proliferation of large, Web-mined text datasets covering hundreds of languages. We manually audit the quality of 205 language-specific corpora released with five major public datasets (CCAligned, ParaCrawl, WikiMatrix, OSCAR, mC4). Lower-resource corpora have systematic issues: At least 15 corpora have no usable text, and a significant fraction contains less than 50% sentences of acceptable quality. In addition, many are mislabeled or use nonstandard/ambiguous language codes. We demonstrate that these issues are easy to detect even for non-proficient speakers, and supplement the human audit with automatic analyses. Finally, we recommend techniques to evaluate and improve multilingual corpora and discuss potential risks that come with low-quality data releases.

Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift. Recent work has tied these shortcomings to beam search – the de facto standard inference algorithm in NMT – and Eikema & Aziz (2020) propose to use Minimum Bayes Risk (MBR) decoding on unbiased samples instead. In this paper, we empirically investigate the properties of MBR decoding on a number of previously reported biases and failure cases of beam search. We find that MBR still exhibits a length and token frequency bias, owing to the MT metrics used as utility functions, but that MBR also increases robustness against copy noise in the training data and domain shift.

The task of document-level text simplification is very similar to summarization with the additional difficulty of reducing complexity. We introduce a newly collected data set of German texts, collected from the Swiss news magazine 20 Minuten (‘20 Minutes’) that consists of full articles paired with simplified summaries. Furthermore, we present experiments on automatic text simplification with the pretrained multilingual mBART and a modified version thereof that is more memory-friendly, using both our new data set and existing simplification corpora. Our modifications of mBART let us train at a lower memory cost without much loss in performance, in fact, the smaller mBART even improves over the standard model in a setting with multiple simplification levels.

Zero-shot neural machine translation is an attractive goal because of the high cost of obtaining data and building translation systems for new translation directions. However, previous papers have reported mixed success in zero-shot translation. It is hard to predict in which settings it will be effective, and what limits performance compared to a fully supervised system. In this paper, we investigate zero-shot performance of a multilingual EN<->FR,CS,DE,FI system trained on WMT data. We find that zero-shot performance is highly unstable and can vary by more than 6 BLEU between training runs, making it difficult to reliably track improvements. We observe a bias towards copying the source in zero-shot translation, and investigate how the choice of subword segmentation affects this bias. We find that language-specific subword segmentation results in less subword copying at training time, and leads to better zero-shot performance compared to jointly trained segmentation. A recent trend in multilingual models is to not train on parallel data between all language pairs, but have a single bridge language, e.g. English. We find that this negatively affects zero-shot translation and leads to a failure mode where the model ignores the language tag and instead produces English output in zero-shot directions. We show that this bias towards English can be effectively reduced with even a small amount of parallel data in some of the non-English pairs.

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.

We present mtrain, a convenience tool for machine translation. It wraps existing machine translation libraries and scripts to ease their use. mtrain is written purely in Python 3, well-documented, and freely available.1

The translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. Recent work on models that have access to information across sentence boundaries has seen only moderate improvements in terms of automatic evaluation metrics such as BLEU. However, metrics that quantify the overall translation quality are ill-equipped to measure gains from additional context. We argue that a different kind of evaluation is needed to assess how well models translate inter-sentential phenomena such as pronouns. This paper therefore presents a test suite of contrastive translations focused specifically on the translation of pronouns. Furthermore, we perform experiments with several context-aware models. We show that, while gains in BLEU are moderate for those systems, they outperform baselines by a large margin in terms of accuracy on our contrastive test set. Our experiments also show the effectiveness of parameter tying for multi-encoder architectures.

We present a task to measure an MT system’s capability to translate ambiguous words with their correct sense according to the given context. The task is based on the German–English Word Sense Disambiguation (WSD) test set ContraWSD (Rios Gonzales et al., 2017), but it has been filtered to reduce noise, and the evaluation has been adapted to assess MT output directly rather than scoring existing translations. We evaluate all German–English submissions to the WMT’18 shared translation task, plus a number of submissions from previous years, and find that performance on the task has markedly improved compared to the 2016 WMT submissions (81%→93% accuracy on the WSD task). We also find that the unsupervised submissions to the task have a low WSD capability, and predominantly translate ambiguous source words with the same sense.

Recently, non-recurrent architectures (convolutional, self-attentional) have outperformed RNNs in neural machine translation. CNNs and self-attentional networks can connect distant words via shorter network paths than RNNs, and it has been speculated that this improves their ability to model long-range dependencies. However, this theoretical argument has not been tested empirically, nor have alternative explanations for their strong performance been explored in-depth. We hypothesize that the strong performance of CNNs and self-attentional networks could also be due to their ability to extract semantic features from the source text, and we evaluate RNNs, CNNs and self-attention networks on two tasks: subject-verb agreement (where capturing long-range dependencies is required) and word sense disambiguation (where semantic feature extraction is required). Our experimental results show that: 1) self-attentional networks and CNNs do not outperform RNNs in modeling subject-verb agreement over long distances; 2) self-attentional networks perform distinctly better than RNNs and CNNs on word sense disambiguation.

We present work on handling XML markup in Statistical Machine Translation (SMT). The methods we propose can be used to effectively preserve markup (for instance inline formatting or structure) and to place markup correctly in a machine-translated segment. We evaluate our approaches with parallel data that naturally contains markup or where markup was inserted to create synthetic examples. In our experiments, hybrid reinsertion has proven the most accurate method to handle markup, while alignment masking and alignment reinsertion should be regarded as viable alternatives. We provide implementations of all the methods described and they are freely available as an open-source framework.