Category Archives: Seminars 2021

Technologies for Translation and Interpreting: Challenges and Latest Developments

Prof Rozane Rebechi, Federal University of Rio Grande do Sul

Small comparable corpora for the retrieval of culture-related elements and their impact for translation

26 February 2021


This talk attempts to share findings of research I have carried out for the past years involving English-Portuguese translation of cultural references. Much has been discussed about the difficulties to translate culture-related elements, after all, “[t]he worlds in which different societies live are distinct worlds, not merely the same world with different labels” (Sapir, 1949: 162). However, semiautomatic investigation of simple and compound keywords retrieved from (small) comparable corpora demonstrate that functional translation (Nord, 2006) of texts of a similar genre in different languages and cultures go far beyond linguistic equivalence, as the specificities of the genre in both languages and cultures should also be considered by translators. To produce texts that work properly for the target reader, the translator should be aware of the domain conventions in both languages and cultures before deciding what aspects should be maintained, adapted, or omitted. Using examples resulting from the analysis of obituaries, cooking recipes, and restaurant reviews (Rebechi, 2018, 2020, 2021), the presentation seeks to demonstrate that the assumptions underlying corpus linguistics may not only help translators to interpret the source language texts, but also assist them in finding solutions for the translation process (Stewart, 2000).


Nord, C. (2006). Loyalty and fidelity in specialized translation. Confluências: Revista de Tradução Científica e Técnica, 29–41.

Rebechi, R. R., & da Silva, M. M. (2018). Obituaries in translation: a corpus-based study. Cadernos de Tradução, 38(3), 298–318.

Rebechi, R., & Tagnin, S. (2020). Brazilian cultural markers in translation: A model for a corpus-based glossary. Research in Corpus Linguistics, 8, 65–85.

Rebechi, R. R.; Schabbach, G. R.; Freitag, P. H. (2021). Sobre a busca por equivalentes funcionais em um corpus comparável português-inglês de críticas gastronômicas. TradTerm, 37(2), 430-459.

Sapir, E. Culture, Language and Personality. Los Angeles: University of California, 1949.

Stewart, D. (2000). Conventionality, Creativity and Translated Text: The Implications of Electronic Corpora in Translation. In M. Olohan (Ed.), Intercultural Faultlines (pp. 73–91). Manchester/Northampton: St. Jerome.


Rozane Rebechi is a professor and researcher at the Federal University of Rio Grande do Sul. She holds a Master and a Ph.D. degrees in English Language and Literature from the University of São Paulo (Brazil). Her main areas of research are Translation, Terminology, and Discourse, to which she applies Corpus Linguistics as methodology. She is currently chair of the Brazilian Association of Researchers in Translation (ABRAPT) and Associated Partner to the European Masters in Technology for Translation and Interpreting (EM TTI). She was recently nominated vice-dean for International Affairs and director of the academic mobility department of UFRGS. Rozane has published several papers in national and international journals and edited volumes on translation and terminology.

Technologies for Translation and Interpreting: Challenges and Latest Developments

Elena Murgolo, Aglatech14

Introducing MT. An LSP workflow

19 February 2021


Have you ever wondered how MT is deployed in an LSP? How do they choose it and test it?

Typically, LSPs are not exactly end-users: the real end-users are either professional translators who need to post-edit MT output or non-language professionals who use it in their daily life, sometimes without even realizing it, as in social media.

Language service providers and translation companies find themselves between developers and end-users. But they are also among the most likely to implement costly solutions, such as trained engines, hosting, and subscriptions, to be able to use cutting-edge technology and high-quality products.

LSPs are also probably the owners of the best data to be used during training and creation of new systems.

Implementing this relatively new technology, however, presents new challenges together with the numerous advantages.

In this talk I will summarize the process and give an overview of what an LSP might be facing when approaching MT and PE and our suggestions based on lessons we learned.


After graduating in Conference Interpreting and working a couple of years as simultaneous and liaison interpreter in fairs and events, Elena Murgolo began working in Aglatech14 as technical translator for German and English. She led the Post-Editing department of the company, and is now Language Technology Team Lead, managing Language Technology deployment and use within the LSP. She and her team are responsible for centralizing and developing LT expertise within the company and with external resources, including freelance translators, vendors, clients, and partner universities.

She is also involved in training new resources in the field of MT, PE, CAT tools and Language Technology in general.

Technologies for Translation and Interpreting: Challenges and Latest Developments

Dr Anna Zaretskaya, TransPerfect

How Good is our MT? A Glimpse into MT Evaluation Challenges in Commercial Settings.

12 February 2021

Abstract: In this presentation we will talk about how machine translation quality is typically evaluated in commercial settings. While there are a lot of good-quality MT systems available for casual and commercial use, translation industry started to pay a lot more attention to MT evaluation. TransPerfect’s customers, typically large organisations, often struggle to find the best way of choosing between different MT providers. In addition, they also want to be sure that the translation quality of the chosen provider is the best they can get, that it brings them maximum ROI, and that the MT quality is improving over time. These are only some of the typical cases that require well-defined MT evaluation methods. While in research such methods already exist (e.g. WMT shared tasks), they are not always directly applicable in commercial scenarios.

Bio: Anna Zaretskaya currently works at TransPerfect as a Senior MT Implementation Manager. In this role she is responsible for designing and implementing MT solutions for TransPerfect clients. She joined the company in 2016 after finishing her PhD in translation technologies and user needs. She has a background in general linguistics (undergraduate studies) and computational linguistics (MS).

Technologies for Translation and Interpreting: Challenges and Latest Developments

Prof Gloria Corpas, University of Wolverhampton

Picking up the Flak: Interpreting-related Technologies in Action

5 February 2021


This talk will revolve around language technologies applied to interpreting. Nowadays there is a pressing need to develop interpreting-related technologies, with practitioners and other end-users increasingly calling for tools tailored to their needs and their new interpreting scenarios. With the advent of new technology, interpreters can work remotely, deliver interpreting in different modes and contexts, on many devices (phones, tablets, laptops, etc.), and even manage bookings and invoice clients with ease. But interpreting as a human activity has resisted complete automation for various reasons, such as fear, unawareness, communication complexities, lack of dedicated tools, etc.

Several computer-assisted interpreting tools and resources for interpreters have been developed, mainly terminology management tools, corpora, and note-taking applications, but they are rather modest in terms of the support they provide. In the same vein, and despite the pressing need to aiding in multilingual mediation, machine interpreting is still under development, with the exception of a few success stories so far.

In this talk, I will present recent R&D projects on interpreting technologies in action. The first one is a speech-to-text system for automating communication of English and Arabic speaking patients in Spanish hospital triage scenarios at A&E services (in progress). The second one is already close to completion. It comprises a suite of NLP-enhanced tools and resources for interpreters and trainees, including but not limited to, terminology tools, corpora building and processing, automatic glossary building, automatic speech recognition and training tools. Final discussion will go back to the two idioms blended in the title of this talk…


BA in German Philology (English) from the University of Malaga. PhD in English Philology from the Universidad Complutense de Madrid (1994). Professor in Translation Technology at the Research Institute in Information and Language Processing (RIILP) of the University of Wolverhampton, UK (since 2007). Professor in Translation and Interpreting at the University of Malaga, Spain (since 2008).  Honorary Adjunct Professor at Xi’an Jiaotong-Liverpool University, China (since 2020). Published and cited extensively, member of several international and national editorial and scientific committees. Her research lines cover computational and corpus-based phraseology, lexicography, corpus-based translation, and language technologies applied to translation and interpreting. Spanish delegate for AEN/CTN 174 and CEN/BTTF 138, actively involved in the development of the UNE-EN 15038:2006 and currently involved in various ISO Standards (ISO TC37/SC2-WG6 “Translation and Interpreting”). Extensive experience in evaluation, validation and quality assurance of University degrees (BA, MA, and Doctorate). Chair of the Evaluation and Verification Commission of the Arts and Humanities field for Madri+d. Consultant for the Spanish Ministry of Research and other University programmes evaluation bodies (ANECA, AQU, ACCUEE, DEVA). President of AIETI (Iberian Association of Translation and Interpreting Studies, 2015-2017), Vice-President of AMIT-A (Association of Women in Science and Technology of Andalusia, 2014-2017), Director of the Department of Translation and Interpreting of the University of Malaga (2016-2021), she is currently Board member of the Advisory council of EUROPHRAS (European Society of Phraseology) and member of the Presidential Committee of AIETI, which is an advisory body of the association.

Technologies for Translation and Interpreting: Challenges and Latest Developments

Dr Vilelmini Sosoni, Ionian University

MT and creative texts: a study of translations, translators’ attitude and readers’ views

29 January 2021


Many of the translation tools in use today were initially designed to cater for technical, repetitive texts. This is still their main niche 25 years after the first versions of these tools appeared. Computer-aided translation (CAT) and Machine translation (MT) were long regarded as unsuitable for the translation of creative texts, which have a predominant expressive or operative function. This means that they exploit the expressive and associative possibilities of language in order to communicate the writer’s thoughts in an artistic, creative way or induce behavioural responses, as stimuli to action or reaction on the part of the reader. Their translation is anything but straightforward, given that it is not sufficient to merely preserve the meaning, but also preserve the reading experience of the original text (Toral and Way, 2018). In other words, the translation of creative texts should “undo the original” (de Man, 1986) to deal with the uniqueness of the source and target languages and source and target audiences. This undoing requires uniquely human skills and does not seem to fit within the dominant translation workflow where a text is fed into an MT engine to be further post-edited by a translator (Lommel and DePalma, 2016).

Lately advances in Neural Machine Translation (NMT) have led to an improved quality of the MT output, especially at the level of fluency (Castilho et al, 2017a; 2017b) even for lexically-rich texts (Bentivogli et al, 2016), and as a result its use for the translation of creative texts is increasingly put to the test. In the present talk, I will attempt to compare the quality of creative texts, i.e. literary and promotional texts, when translated from scratch with their quality following an MT and PE scenario, based on a fine-grained human error analysis. I will also investigate the translators’ attitudes and perceptions vis-à-vis MT and PE of creative texts and the texts’ reception by average readers.


Bentivogli, Luisa, Andriana Bisazza, Mauro Cettolo, Marcello Federico. 2016. Neural versus phrase-based machine translation quality: a case study. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, pp 257–267

Castilho, Sheila, Joss Moorkens, Federico Gaspari, Rico Sennrich, Vilelmini Sosoni, Panayota Georgakopoulou, Pintu Lohar, Andy Way, Antonio Valerio Miceli Barone, Maria Gialama. 2017a. “A Comparative Quality Evaluation of PBSMT and NMT using Professional Translators.” MT Summit 2017, Nagoya, Japan.

Castilho, Sheila, Joss Moorkens, Federico Gaspari, Iacer Calixto, John Tinsley, Andy Way. 2017b. “Is Neural Machine Translation the New State of the Art?” The Prague Bulletin of Mathematical Linguistics 108: 109-120.

Lommel, Arle, Donald A. DePalma. 2016. Europe’s leading role in Machine Translation: How Europe is driving the shift to MT. Technical report. Common Sense Advisory, Boston.


Dr Vilelmini Sosoni is Senior Lecturer at the Department of Foreign Languages, Translation and Interpreting at the Ionian University in Corfu, Greece, where she teaches Legal and Economic Translation, EU texts Translation and Terminology, Translation Technology, Translation Project Management and Audiovisual Translation (AVT). In the past, she taught Specialised Translation in the UK at the University of Surrey, the University of Westminster and Roehampton University, and in Greece at the National and Kapodistrian University of Athens and the Institut Français d’ Athènes.  She also has extensive industrial experience having worked as translator, editor, subtitler and intepreter. She holds a BA in English Language and Linguistics from the National and Kapodistrian University of Athens, an MA in Translation and a PhD in Translation and Text Linguistics from the University of Surrey. Her research interests lie in the areas of Translation of Institutional Texts, Machine Translation (MT), Corpus Linguistics, Cognitive Studies, and AVT. She is a founding member of the Research Lab “Language and Politics” of the Ionian University and a member of the “Centre for Research in Translation and Transcultural Studies” of Roehampton University. She has participated in several EU-funded projects, notably TraMOOC, Eurolect Observatory and Training Action for Legal Practitioners: Linguistic Skills and Translation in EU Competition Law, while she has edited several volumes and books on translation and published numerous articles in international journals and collective volumes.

Technologies for Translation and Interpreting: Challenges and Latest Developments

Dr Claudia Lecci, University of Bologna

Creating terminological projects for the detection of in-domain terminology: a workflow for interpreters.

27 January 2021


Interpreters, as well as translators, need to be familiar with all the skills and abilities necessary to create a terminological project and detect the terminology belonging to specific domains of the orality genre.

The typical approach for detecting specialized terminology can be described through a workflow which combines different stages, starting from an information mining stage and ending with the creation of a terminological resource, namely a glossary or a terminology database that, when needed, can also be combined with Computer Assisted Translation tools.

The workflow presented in this talk starts with the definition of a domain and with the collection of reference materials on the Internet. The second step consists in the construction of specialized comparable corpora from the web using a dedicated tool. The third stage is the corpus-based extraction of simple or complex terms with the help of a concordancing tool. The last step of the workflow is the creation of terminological entries organized in the form of glossaries and/or TermBases.

The insights gained from this presentation will help trainee and professional interpreters prepare terminological resources both for specific assignments and for more general topics.


Claudia Lecci graduated in Specialised Translation and Translation for the Publishing Industry at the Advanced School of Modern Languages for Interpreters and Translators (now Department of Interpreting and Translation – DIT).

She currently teaches the MA modules “Computer-assisted Translation and web localization” and “Machine Translation and Post-Editing” within the Master’s in Specialized Translation (DIT – Forlì) and coordinates the MA course “Methods and Technologies for Interpreting” within the Master’s in Interpreting (DIT- Forlì). She also teaches the course “Traduzione in Italiano dall’Inglese (assistita)” as part of the Bachelor’s in Intercultural and Linguistic Mediation (DIT – Forlì).

She is an SDL Trados Authorised Trainer for SDL Trados Studio 2021 and SDL MultiTerm 2021.