Category Archives: Seminars 2021

Technologies for Translation and Interpreting: Challenges and Latest Developments

Dr Konstantinos Chatzitheodorou, Strategic Agenda

Using technology in the translation quality assessment

19 March 2021

Abstract: The process of determining translation quality is subjective and relies on human judgments. Translation quality is affected by a variety of factors that are weighted differently in each translation task and can be viewed from different perspectives. Hence, it is not equally measurable or assessable (Almutairi, 2018). The talk will emphasize the importance of measuring translation quality and how it can be accomplished. The first part of the presentation will introduce different frameworks and software used in the process of translation evaluation focusing on error classification schemes available in both professional and academic word. The second part of the presentation will include a demonstration of Træval which is a Software-as-a-Service (SaaS) that allows humans to evaluate translation outputs. By providing an easy-to-use graphical interface, it assists researchers and users in this process. In particular, three different scenarios will be presented using the Dynamic Quality Framework – Multidimensional Quality Metrics (DQF-MQM) error typology (Lommel, 2018): an evaluation of a simple translation task, an evaluation task focused on the assessment of multi-word units, and, finally, a technology-aided evaluation task aiming to reduce subjectivity.

Dr Konstantinos Chatzitheodorou is a postdoctoral researcher at the Department of Foreign Languages, Translation and Interpreting, Ionian University. He received his PhD in Applied Translation Studies and Computational Linguistics from the Aristotle University of Thessaloniki. He holds a BA in Italian Language and Literature from the School of Italian Language and Literature, Aristotle University of Thessaloniki and an MSc in Informatics in Humanities from the Department of Informatics, Ionian University. He is also ECQA Certified Terminology Manager – Engineering. He is employed as a Computational Linguist in the private sector, assisting organizations to use language data to gain strategic insights. He has also worked as a Machine Translation Expert and Terminologist at the European Parliament – Directorate-General for Translation in Luxembourg. Over the years, Konstantinos has also contributed as a researcher to several EU projects in areas of his interest.


Almutairi, M.O.L., 2018. The objectivity of the two main academic approaches of translation quality assessment: arab spring presidential speeches as a case study (Doctoral dissertation, University of Leicester).

Chatzitheodorou, K. and Chatzistamatis, S, 2013. COSTA MT evaluation tool: An open toolkit for human machine translation evaluation. The Prague Bulletin of Mathematical Linguistics, 100(2013), pp.83-89.

Lommel, A., 2018. Metrics for translation quality assessment: a case for standardising error typologies. In Translation Quality Assessment (pp. 109-127). Springer, Cham.

Secară, A., 2005, March. Translation evaluation: A state of the art survey. In Proceedings of the eCoLoRe/MeLLANGE workshop, Leeds (Vol. 39, p. 44).

Technologies for Translation and Interpreting: Challenges and Latest Developments

Fardad Zabetian (CEO of KUDO)

Multilingual communication is evolving and how KUDO is part of the evolution.

12 March 2021


During this 45min talk, Fardad will share his journey in the world of multilingual meetings in the last 20 years, how he sees the market is evolving, the new opportunities for businesses and  interpreters . He will cover the new KUDO Marketplace and how this new system going to remove friction points in accessing interpreting services. He will cover the challenges in the new uses cases such as short notice for assignments and how technology and AI will assist interpreters to prepare in shorter time.


A visionary entrepreneur, Fardad has founded and placed two companies among the fastest growing business in America. He has also expanded to key markets over Europe and Asia. Fardad is no stranger to big challenges. In 2012, he was part of the design and roll-out a complete makeover of the United Nation’s meeting facilities, including the general assembly hall in New York. He has also played a key supporting role as a high-end equipment provider to various iterations of the IMF/ World Bank Annual Meetings and several European Institutions. in 2016, Fardad co-founded AVAtronics, a Swiss technology company focusing on active noise canceling technology. In 2017, Fardad founded KUDO, where he now takes the meeting experience beyond the room to connect businesses and people in true border-less fashion, without language or geographic constraints.

Natural Language Processing

Dr Sanja Štajner, ReadableAI

Automatic Assessment of Conceptual Text Complexity Using Knowledge Graphs

8 March 2021


In this talk,  I will present in depth the ideas behind our position paper on “Automatic Assessment of Conceptual Text Complexity Using Knowledge Graphs“ that was published at COLING 2018. First, I will define what we consider under conceptual complexity of texts, what is its role in text understanding, and why it is important to have an automatic way of assessing it. Next, I will introduce in details a number of graph-based measures on a large knowledge base that we proposed as features for automatic assessment of conceptual complexity, and talk about the experimental setup and results. By using a high-quality language learners corpus for English, we showed that graph-based measures of individual text concepts, as well as the way they relate to each other in the knowledge graph, have a high discriminative power when distinguishing between two versions of the same text. Furthermore, when used as features in a binary classification task aiming to choose the simpler of two versions of the same text, our measures achieved high performance even in a default setup.


Sanja Štajner is currently Chief Research Scientist at ReadableAI and Senior Research Scientist at Symanto. She has obtained her PhD in Computer Science on the topic of Data-Driven Text Simplification from University of Wolverhampton (UK), and holds a multiple Masters degree in Natural Language Processing and Human Language Technologies.

Sanja is one of the most cited researches in the field of Text Simplification, with over 80 peer-reviewed articles in international journals and top-tier NLP/AI conferences, holds several awards at international conferences for her work in text simplification, and is regularly invited as a speaker across academia and industry. She has served as an area chair, reviewer, and member of the scientific committee in many top-tier international NLP/AI conferences, and was the lead organizer of two shared tasks in the field of text simplification (QATS 2016 and CWI 2018).

Technologies for Translation and Interpreting: Challenges and Latest Developments

Dr Arda Tezcan, Ghent University

Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation

8 January 2021


Even though Machine Translation (MT) quality may have increased considerably over the past years, most notably with advances in the field of Neural Machine Translation (NMT), Translation Memories (TMs) still offer some advantages over MT systems. They are not only able to translate previously seen sentences ‘perfectly’ but they also offer ‘near perfect’ translation quality when highly similar source sentences are retrieved from

the TM. As a result, in Computer-Assisted Translation (CAT) workflows, the MT system is often used as a back-off mechanism when the TM fails to retrieve high fuzzy matches above a certain threshold, even though it has been shown that this basic integration method is not always the most optimal TM-MT combination strategy.

We present a simple yet powerful data augmentation method for boosting Neural Machine Translation (NMT) performance by leveraging information retrieved from a Translation Memory (TM). Tests on the DGT-TM data set for multiple language pairs show consistent and substantial improvements over a range of baseline systems. The results suggest that this method is promising for any translation environment in which a sizeable TM is available and a certain amount of repetition across translations is to be expected, especially considering its ease of implementation.    

Machine Learning/Deep Learning

Dr Siva Reddy, McGill University

Pathological Behaviours of Large Neural Models of Language

2 March 2021


Large neural models of language have achieved state-of-the-art results on many NLP tasks like Question Answering. Despite this progress, they are known to be surprisingly brittle to variations of input. In this talk, we will systematically study the pathological behaviours of neural models in three scenarios: generalization to natural language sentence structure, generalization in reasoning strategies, and latent capture of societal biases.


Siva Reddy is an Assistant Professor in the School of Computer Science and Linguistics at McGill University. He is a Facebook CIFAR AI Chair and a core faculty member of Mila Quebec AI Institute. Before McGill, he was a postdoctoral researcher in the Computer Science Department, Stanford University. He received his PhD from the University of Edinburgh in 2017, where he was a Google PhD Fellow. His research focuses on Natural Language Processing and Computational Linguistics. He received the 2020 VentureBeat AI Innovation Award in NLP.

Technologies for Translation and Interpreting: Challenges and Latest Developments

Yves Champollion, Founder of Wordfast

“Machine Translation for us Human Translators: Good, Bad, or Ugly?”

5 March 2021


The author starts with defining the limits and scope of MT as used by translators, as compared with other uses of MT.

Then he briefly gives an overview of the various implementations of MT for translators in the past 25 years, and the typical reactions from translators.

He will review the situation with every generation of MT, discussing MT gains, acceptance, but also pain points and fears.

The last part will focus on the current state of MT in the translation industry: the strategic aspect of MT for agencies and corporations, the economics of MT, the gain or pain on a translator’s side.


Yves Champollion has over 30 years experience as a pioneer in the translation and localization industry. Since 1982, Champollion has worked in his native France as a freelance translator in the science field. His languages include French, Latin, German, English , Spanish, Portuguese and Russian as well as some Japanese and Shangana, a Zulu-related language of Southern Mozambique. In 1996, Champollion began working as a project manager and consultant for leading translation agencies, handling large-scale projects for IBM and Microsoft. He began developing software in the 1980’s and in 1999, he developed Wordfast, an MS Word-based translation memory tool. As the author of several articles on translation and the speaker at a number of high-profile industry events, Champollion is an esteemed voice and well-respected figure in the language services industry.