Round-Trip Translation: A Method for Estimating Revision and Editing Difficulty of English as a Lingua Franca Academic Texts

Tedesco, Novella (2022) Round-Trip Translation: A Method for Estimating Revision and Editing Difficulty of English as a Lingua Franca Academic Texts. [Laurea magistrale], Università di Bologna, Corso di Studio in Specialized translation [LM-DM270] - Forli'
Documenti full-text disponibili:
[img] Documento PDF (Thesis)
Disponibile con Licenza: Salvo eventuali più ampie autorizzazioni dell'autore, la tesi può essere liberamente consultata e può essere effettuato il salvataggio e la stampa di una copia per fini strettamente personali di studio, di ricerca e di insegnamento, con espresso divieto di qualunque utilizzo direttamente o indirettamente commerciale. Ogni altro diritto sul materiale è riservato

Download (2MB)


The aim of this work is to examine the feasibility of automatically evaluating English as a Lingua Franca (ELF) academic writing for revision purposes in the context of the publishing industry, thus optimizing the performance of revisors and minimizing the costs and time needed to plan the revision workflow. The study also represents a starting point for achieving fairer and standardized revisor rates. The dissertation has two main objectives: on the one hand, shedding light on some theoretical issues regarding English linguistics and revision, which provide the background for the practical developments of this work. In particular, the concept of English as a lingua franca is framed in the context of international academic communication in the era of post-globalization. Machine translation and technological tools for revision are also analyzed from a theoretical perspective. On the other hand, this study encompasses the design, implementation and testing of an automatic method for a priori evaluation of revision difficulty, based on the similarity between a source text and its round-trip translation (RTT). Accordingly, the experiments and the work carried out at Bologna University Press (BUP) have had the aim of developing specialized methods for revision difficulty evaluation. Nonetheless, the variety of data used in the experiments demonstrates the applicability of the method beyond the cases under study. The results show that the RTT-based method, in conjunction with the BLEU score as a text similarity measure, can be successfully used to estimate revision difficulty, although further tests are needed before this method can be implemented in real working settings. These reflections are included in the discussion of each set of experiments, leading to the final remarks and further developments of the study. The application of RTT for language learning is also briefly considered as a way of generalizing about the potentials of this innovative method

Tipologia del documento
Tesi di laurea (Laurea magistrale)
Autore della tesi
Tedesco, Novella
Relatore della tesi
Correlatore della tesi
Corso di studio
Ordinamento Cds
Parole chiave
revision, academic writing, machine translation, round-trip translation, text similarity metrics, English as a lingua franca, automatic evaluation, revision difficulty.
Data di discussione della Tesi
15 Marzo 2022

Altri metadati

Statistica sui download

Gestione del documento: Visualizza il documento