Issues and challenges of automated translation of literary texts

Key information

Date
Venue
Russell Square: College Buildings
Room
G51A

About this event

Speaker:

Alina Tenescu (University of Craiova)

Abstract

The new generation of students, “the digital natives”, answers more easily and effectively to mixed learning, combining the classic classroom sessions with computer-based training and web-based training (CBT and WBT). This education facilitates the development of digital skills with students and increases the level of knowledge and handling of online tools – of automatic translators, for example, with students in foreign languages and translation, parallelly with the improvement of their textual competence and of their critical thinking on the issues and problems of translation. The first aim of our study is to analyze the most frequent errors in automatic translation, errors which can be identified by students in career training (translation and interpreting) and by professional translators as they carry out the translation of a literary text from English to French (“version”), following the automatic processing of a paragraph by two translation memory software applications (Google Translate and Systran), with the help of the evaluation metric SAE J2450. The second objective of our study is to analyze the quality of the translations (from English to French) provided following the automatic processing of the texts in our corpus by the two translation memory software applications (statistic and hybrid) using BLEU evaluation metric.

Finally, we will compare the scores obtained following the evaluation of translation quality and accuracy using the two metrics, while at the same time proposing a course or path making use of a pedagogical method that provides translation students with the necessary ICT tools in order to develop their analytic thinking and improve their knowledge on the existing differences between the quality of translations carried out by different translation engines, as well as on the errors and uncertainties of each software.

Biography

Alina Ţenescu is Reader PhD at the Faculty of Letters, University of Craiova, Romania. She holds a BA (French major–English minor) and a BSc in Communication and Public Relations, as well as two MA degrees (in French literature and Intercultural communication) and one MSc degree in Business management and communication. She defended her PhD thesis in 2008 and her postdoctoral research focused on the perception and representation of space and place in postmodern Francophone literature.

Her areas of interest are: postmodern English-American and Francophone literature, the semiotics of space, cognitive metaphors in literature and media discourse, discourse analysis, the anthropology of supermodernity, advertising, mass and intercultural communication, automated translation. She is a member of AFJSC (Association of Trainers in Journalism and Communication) and AEEF (European Association of Francophone Studies).