Cross-linguistic Mediated Communication: Hybrid Text Production English-Spanish

This book shows how corpus-based cross-linguistic studies contribute to the building and optimising multilingual hybrid text production. It highlights the implications of leveraging LLMs for the automatic generation of domain-specific texts. It addresses the new challenges and opportunities raised by AI-enhanced data augmentation and post-editing.

Hybrid text production today comprises machine translation chunks, human-produced paragraphs modelled on the writer's L1, and generative AI contributions via prompting. This book explores how corpus-based cross-linguistic studies can contribute to building and optimising Natural Language Generation in multilingual contexts. The aim is to show how rich linguistic annotation can provide valuable data to enhance and refine hybrid text production. Corpus data are mined from CLANES, a multilayer English-Spanish comparable corpus annotated for PoS, semantic, rhetorical and pragmatic information. The study highlights the implications of leveraging LLMs for the automatic generation of domain-specific texts. It also addresses the new challenges and opportunities raised by AI-enhanced data augmentation and post-editing, stressing the need for human control over text generation.

Autorentext

Rosa Rabadán is a Professor at the Department of Modern Languages at the University of León, Spain. Her areas of interest include corpus-based contrast English-Spanish, translation, and language technology. Noelia Ramón is an Associate Professor of English at the University of León. She is the current leader of the ACTRES research group, engaged in producing expert language data for the development of text-production applications in specialised domains.