Articles

AbstractWe present the CUNI-Bergamot submission for the WMT22 General translation task. We compete in English-Czech direction. Our submission further explores block backtranslation techniques. Compared to the previous work, we measure performance in terms of COMET score and named entities translation accuracy. We evaluate performance of MBR decoding compared to traditional …...

AbstractAdditive interventions are a recently-proposed mechanism for controlling target-side attributes in neural machine translation by modulating the encoder’s representation of a source sequence as opposed to manipulating the raw source sequence as seen in most previous tag-based approaches. In this work we examine the role of additive interventions in a …...

AbstractFor real-life applications, it is crucial that end-to-end spoken language translation models perform well on continuous audio, without relying on human-supplied segmentation. For online spoken language translation, where models need to start translating before the full utterance is spoken,most previous work has ignored the segmentation problem. In this paper, we …...

AbstractThe cornerstone of multilingual neural translation is shared representations across languages. Given the theoretically infinite representation power of neural networks, semantically identical sentences are likely represented differently. While representing sentences in the continuous latent space ensures expressiveness, it introduces the risk of capturing of irrelevant features which hinders the learning …...

AbstractNon-autoregressive (NAR) machine translation has recently received significant developments and now achieves comparable quality with autoregressive (AR) models on some benchmarks while providing an efficient alternative to AR inference. However, while AR translation is often used to implement multilingual models that benefit from transfer between languages and from improved serving …...

AbstractIt has been found that NMT systems have a strong preference towards social defaults and biases when translating certain occupations, which due to their widespread use, can unintentionally contribute to amplifying and perpetuating these patterns. In that sense, this work focuses on sentence-level gender agreement between gendered entities and occupations …...

AbstractWe present a collection of expanded human annotations of the WMT20 English-Inuktitut machine translation shared task, covering the Nunavut Hansard portion of the dataset. Additionally, we recompute News rankings to take into account the completed set of human annotations and certain irregularities in the annotation task construction. We show the …...

AbstractSimultaneous speech translation (SST) can be evaluated on simulated online events where human evaluators watch subtitled videos and continuously express their satisfaction by pressing buttons (so called Continuous Rating). Continuous Rating is easy to collect, but little is known about its reliability, or relation to comprehension of foreign language document …...

AbstractIn MT evaluation, pairwise comparisons are conducted to identify the better system. In conducting the comparison, the experimenter must allocate a budget to collect Direct Assessment (DA) judgments. We provide a cost effective way to spend the budget, but show that typical budget sizes often do not allow for solid …...

AbstractWe present a very simple method for extending pretrained machine translation metrics to incorporate document-level context. We apply our method to four popular metrics: BERTScore, Prism, COMET, and the reference-free metric COMET-QE. We evaluate our document-level metrics on the MQM annotations from the WMT 2021 metrics shared task and find …...

AbstractWe 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 …...

AbstractThe machine translation efficiency task challenges participants to make their systems faster and smaller with minimal impact on translation quality. How much quality to sacrifice for efficiency depends upon the application, so participants were encouraged to make multiple submissions covering the space of trade-offs. In total, there were 76 submissions …...

AbstractWe report the results of the WMT 2022 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. This edition introduces a few novel aspects and extensions …...

AbstractThis 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 …...

AbstractThis paper presents the results of the General Machine Translation Task organised as part of the Conference on Machine Translation (WMT) 2022. 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 four …...

The COVID-19 pandemic has drastically affected various industries, and aviation is the hardest hit (Suau-Sanchez et al., 2020). This predicament has turned all flyers across the globe into flying a low-cost carrier (henceforth, LCC) for pragmatic reasons. Attracting airline customers in a competitive market during this extra challenging time is …...

For the last two years, from 2020 to 2021, COVID-19 has broken disease prevention measures in many countries, including Viet- nam, and negatively impacted various aspects of human life and the social community. Be- sides, the misleading information in the com- munity and fake news about the pandemic are also …...

Generating a paragraph from an image is a complex task that requires object and activ- ity recognition. It is now feasible because of recent advances in image captioning. Sum- marizing an image into a single sentence can only provide a superficial description of the visual information included within the image. …...

A vehicle recall system is a process of recall- ing and repairing vehicles with defective de- signs or potential for accidents and failures. The recall document concisely explains the circumstances and causes of product defects. This paper presents two types of annotations on public vehicle recall reports, part entities and …...

Spoken language understanding (SLU) sys- tems using deep learning techniques require ef- fective intent detection and slot filling models. Previous studies in this field taking advantage of sequence to sequence models have achieved good results. However, they focus on the local- ity of words and thus are sensitive to surround- …...