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

Fine-tuning pretrained LLMs has been shown to be an effective strategy for reaching state-of-the-art performance on specific tasks like machine translation. However, this process of adaptation often implies sacrificing general-purpose…

Learned metrics such as BLEURT have in recent years become widely employed to evaluate the quality of machine translation systems. Training such metrics requires data which can be expensive and difficult to acquire, particularly for…

Machine Translation Quality Estimation is a notoriously difficult task, which lessens its usefulness in real-world translation environments. Such scenarios can be improved if quality predictions are accompanied by a measure of uncertainty.…

Service manual documents are crucial to the engineering company as they provide guidelines and knowledge to service engineers. However, it has become inconvenient and inefficient for service engineers to retrieve specific knowledge from…

Data preparation is a critical step in enhancing the usability of tabular data and thus boosts downstream data-driven tasks. Traditional methods often face challenges in capturing the intricate relationships within tables and adapting to…

We analyze the ability of pre-trained language models to transfer knowledge among datasets annotated with different type systems and to generalize beyond the domain and dataset they were trained on. We create a meta task, over multiple…

Public models offer predictions to a variety of downstream tasks and have played a crucial role in various AI applications, showcasing their proficiency in accurate predictions. However, the exclusive emphasis on prediction accuracy may not…

We present an approach to neural machine translation (NMT) that supports multiple domains in a single model and allows switching between the domains when translating. The core idea is to treat text domains as distinct languages and use…

We propose iteratively prompting a large language model to self-correct a translation, with inspiration from their strong language understanding and translation capability as well as a human-like translation approach. Interestingly,…

The effective and ethical use of data to inform decision-making offers huge value to the public sector, especially when delivered by transparent, reproducible, and robust data processing workflows. One way that governments are unlocking…

Maturity models for software indicate the key areas that contribute to quality improvements. They usually combine technical, organisational and human aspects relevant for effective software development, to focus the efforts and draw the…

Translate-test is a popular technique to improve the performance of multilingual language models. This approach works by translating the input into English using an external machine translation system, and running inference over the…

Data is the most powerful decision-making tool at our disposal. However, despite the exponentially growing volumes of data generated in the world, putting it to effective use still presents many challenges. Relevant data seems to be never…

While open source communities attract diverse contributors across the globe, only a few open source software repositories provide essential documentation, such as ReadMe or CONTRIBUTING files, in languages other than English. Recently,…

Although proper handling of discourse significantly contributes to the quality of machine translation (MT), these improvements are not adequately measured in common translation quality metrics. Recent works in context-aware MT attempt to…

Professional translators often dictate their translations orally and have them typed afterwards. The TransTalk project aims at automating the second part of this process. Its originality as a dictation system lies in the fact that both the…

The overall translation quality reached by current machine translation (MT) systems for high-resourced language pairs is remarkably good. Standard methods of evaluation are not suitable nor intended to uncover the many translation errors…

"Data" is becoming an indispensable production factor, just like land, infrastructure, labor or capital. As part of this, a myriad of applications in different sectors require huge amounts of information to feed models and algorithms…

While quality estimation (QE) can play an important role in the translation process, its effectiveness relies on the availability and quality of training data. For QE in particular, high-quality labeled data is often lacking due to the high…

Despite the remarkable progress of modern machine translation (MT) systems on general-domain texts, translating structured LaTeX-formatted documents remains a significant challenge. These documents typically interleave natural language with…