Leonardo Zilio

Dr Leonardo Zilio

Technical Specialist (Translation Technologies and Data)



Research interests

Research projects


LEONARDO ZILIO, Maria Jose Bocorny Finatto, Renata Vieira Named Entity Recognition Applied to Portuguese Texts from the XVIII Century, In: Proceedings of the Second Workshop on Digital Humanities and Natural Language Processing (2nd DHandNLP 2022) co-located with International Conference on the Computational Processing of Portuguese (PROPOR 2022)3128

Extracting data and knowledge dispersed along Portuguese old medical records is important especially for researchers dealing with historical epidemiology and health sciences. An essential task in Natural Language Processing for processing textual information is Named En- tity Recognition (NER). In this paper, our main objective is to test the performance of NER systems for Portuguese for extracting information from XVIII-century medical texts, so that we can provide an annotated version of an important work of this type.

Joanna Gough, Özlem Temizöz, Graham Hieke, Leonardo Zilio (2023)Concurrent Translation on Collaborative Platforms, In: Translation Spaces John Benjamins

The advent of AI-supported, cloud-based collaborative translation platforms have enabled a new form of online collaborative translation — ‘concurrent translation’ (CT). CT refers to commercial translation performed on such platforms by multiple agents (translators, editors, subject-matter experts etc) simultaneously, via concurrent access. Although the practice has recently gained more ground, research on CT is scarce. The present article reports on selected key findings of a study that investigates translators experiences with CT via a survey of 804 professional translators working in CT mode across different commercial platforms. Despite the affordances such as peer learning, positive competition, speed, flexibility of the volume of work and working time, and reduced responsibility and reduced stress, CT workflow comes with its substantial challenges such as time pressure, negative competition, reduced selfrevision and research, all of which result in quality compromised for speed.

Leonardo Zilio, Liana Braga Paraguassu, Luis Antonio Leiva Hercules, Gabriel L. Ponomarekano, Laura P. Berwanger, Maria Jose Bocorny Finatto (2020)A Lexical Simplification Tool for Promoting Health Literacy, In: 1st Workshop on Tools and Resources to Empower People with REAding DIfficulties (READI2020)

This paper presents MedSimples, an authoring tool that combines Natural Language Processing, Corpus Linguistics and Terminologyto help writers to convert health-related information into a more accessible version for people with low literacy skills. MedSimplesapplies parsing methods associated with lexical resources to automatically evaluate a text and present simplification suggestions thatare more suitable for the target audience. Using the suggestions provided by the tool, the author can adapt the original text and makeit more accessible. The focus of MedSimples lies on texts for special purposes, so that it not only deals with general vocabulary, butalso with specialized terms. The tool is currently under development, but an online working prototype exists and can be tested freely.An assessment of MedSimples was carried out aiming at evaluating its current performance with some promising results, especially forinforming the future developments that are planned for the tool.

Liana Paraguassu, Leonardo Zilio, Luis Antonio Leiva Hercules, Maria Jose Bocorny Finatto (2020)MedSimples: An Automated Simplification Toolfor Promoting Health Literacy in Brazil, In: DHandNLP@PROPOR 2020

Additional publications