Proceedings for the First Workshop on Modelling Translation: Translatology in the Digital Age
Bizzoni, Yuri; Teich, Elke; España-Bonet, Cristina; van Genabith, Josef; (Ed.): Association for Computational Linguistics, online, 2021.
Translatology is the theoretical and practical study of translation. It combines insights from linguistics, the humanities, cognitive and computer science to understand the process of translating between languages and the particular features characterizing language in translation. Central concepts of contemporary translatology are translationese, linguistic patterns that tend to make translations more similar to each other than to texts originally written in their target language; and variation, which refers to the fact that different types of translations, such as written translations vs. interpreting, display systematic linguistic differences.
The Workshop on Modelling Translation: Translatology in the Digital Age seeks to facilitate collaboration and knowledge exchange between researchers in linguistics, AI, CL, NLP, translation studies, cognitive and computer science focusing on modeling translation from diverse angles, such as variation in translation, machine translation, translation quality assessment and translationese. Specifically, the workshop aims to foster innovative research at the intersection between machine and human translation modeling by applying concepts from translation studies to machine translation or using machine translation techniques to explore research questions in translatology. We encourage research on modeling aspects of translation, including word embeddings, neural or statistical machine translation, feature-based text classification, syntactic and semantic parsing, monolingual or multilingual language models, text generation, and stylometry. Our Call for Papers elicited contributions from a heterogeneous group of researchers. We are very happy to present 11 papers from diverse fields such as computational linguistics, computer science, and translation studies.
The papers cover topics ranging from the creation of more reliable interpreting corpora to the study of sentiment intensity in alternative translations. Major themes include a focus on methods to evaluate and explain linguistic variation in translations, new quantitative and experimental approaches, the creation of tools for translators and translation research and the need for data and corpora to better study translators’ choices in all their aspects.
This workshop would not have been possible without the contributions of both authors and reviewers. We would like to thank everyone who submitted their work to this workshop and the program committee for their extensive and helpful reviews.
We would also like to thank our invited speakers, Jörg Tiedemann (University of Helsinki) and Markus Freitag (Google), for sharing their insights on this fascinating topic. Finally, we would like to thank all the attendees of the workshop. All of this contributes to a truly enriching event!