Related papers: A Maturity Model for Public Administration as Open…

Many works proposed methods to improve the performance of Neural Machine Translation (NMT) models in a domain/multi-domain adaptation scenario. However, an understanding of how NMT baselines represent text domain information internally is…

Despite the known limitations, most machine translation systems today still operate on the sentence-level. One reason for this is, that most parallel training data is only sentence-level aligned, without document-level meta information…

Continuous evolution in modern software often causes documentation, tutorials, and examples to be out of sync with changing interfaces and frameworks. Relying on outdated documentation and examples can lead programs to fail or be less…

Sensitive personal information of individuals and non-personal information of organizations or communities often needs to be legitimately exchanged among different stakeholders, to provide services, maintain public health, law and order,…

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

Generative Pre-trained Transformer (GPT) models have shown remarkable capabilities for natural language generation, but their performance for machine translation has not been thoroughly investigated. In this paper, we present a…

Inspired by the inductive transfer learning on computer vision, many efforts have been made to train contextualized language models that boost the performance of natural language processing tasks. These models are mostly trained on large…

There are visible changes in the world organization, environment and health of national conscience that create a background for discussion on possible redefinition of global, state and regional management goals. The author applies the…

As complex software and systems development projects need models as an important planning, structuring and development technique, models now face issues resolved for software earlier: models need to be versioned, differences captured,…

Recent studies have proven that the training of neural machine translation (NMT) can be facilitated by mimicking the learning process of humans. Nevertheless, achievements of such kind of curriculum learning rely on the quality of…

Global e-retailing continues to gain in popularity, but little attention is being paid to the role of translation. This paper proposes a study investigating whether improving translated information quality of product descriptions increases…

Transparency regarding the processing of personal data in online services is a necessary precondition for informed decisions on whether or not to share personal data. In this paper, we argue that privacy interfaces shall incorporate the…

Most languages lack sufficient data for large-scale monolingual pretraining, creating a "data wall." Multilingual pretraining helps but is limited by language imbalance and the "curse of multilinguality." An alternative is to translate…

Assessing and improving the quality of data are fundamental challenges for data-intensive systems that have given rise to applications targeting transformation and cleaning of data. However, while schema design, data cleaning, and data…

To address the need for regulating digital technologies without hampering innovation or pre-digital transformation regulatory frameworks, we provide a model to evolve Data governance toward Information governance and precise the relation…

Data volumes and rates of research infrastructures will continue to increase in the upcoming years and impact how we interact with their final data products. Little of the processed data can be directly investigated and most of it will be…

Evolutionary change over time in the context of data pipelines is certain, especially with regard to the structure and semantics of data as well as to the pipeline operators. Dealing with these changes, i.e. providing long-term maintenance,…

Topic models are often used to identify human-interpretable topics to help make sense of large document collections. We use knowledge distillation to combine the best attributes of probabilistic topic models and pretrained transformers. Our…

Converging societal and technical factors have transformed language technologies into user-facing applications used by the general public across languages. Machine Translation (MT) has become a global tool, with cross-lingual services now…

The inception of large language models has helped advance state-of-the-art performance on numerous natural language tasks. This has also opened the door for the development of foundation models for other domains and data modalities such as…