Confirmed presentations (updated to 17 August 2017)
* Lists subject to changes
Roberto Navigli
He was also a co-PI of a Google Focused Research Award on NLP. In 2015 he received the META prize for groundbreaking work in overcoming language barriers withBabelNet, a project also highlighted in TIME magazine and presented in the most cited 2012 paper in the Artificial Intelligence Journal, a journal for which he is currently an Associate Editor. Based on the success of BabelNet and its multilingual disambiguation technology, he co-founded Babelscape, a Sapienza startup company which enables HLT in hundreds of languages. |
KEYNOTE - From text to concepts and back: going multilingual with BabelNet in a step or two In this talk I will introduce the most recent developments of the BabelNet technology, winner of several scientific awards and of great interest to interpreters and translators. I will first describe BabelNet live – the largest, continuously-updated multilingual encyclopedic dictionary – and then discuss a range of cutting-edge industrial use cases implemented by Babelscape, our Sapienza startup company, including: multilingual interpretation and mapping of terms; multilingual concept and entity extraction from text; semantically-enhanced multilingual translation, and cross-lingual text similarity. |
Geoffrey Westgate
|
WIPO Pearl - The terminology portal of the World Intellectual Property Organization In this paper we shall present WIPO Pearl, the multilingual terminology portal of the World Intellectual Property Organization, a specialized agency of the United Nations. The nature of the linguistic dataset made available in WIPO Pearl will be described and we shall show how multilingual knowledge representation is achieved and graphically displayed. Secondly, we shall demonstrate how such data is exploited to facilitate search of prior art for patent filing or examination purposes, by leveraging the validated linguistic content as well as the validated conceptual relations that are presented in “concept maps”. We shall discuss how, in addition to humanly validated concept maps, “concept clouds” are generated by means of machine learning algorithms which automatically cluster concepts in the database by exploiting textual data embedded in the terminology repository. And finally, we shall present opportunities for collaborations with WIPO in the field of terminology. |
Carlos Teixeira, Joss Moorkens, Daniel Turner, Joris Vreeke and Andy Way
|
Creating a tool for multimodal translation and post-editing on touch-screen devices Only a few translation tools have been created with an ‘organic’ integration of TM and MT, i.e. tools that were designed to work equally well for post-editing MT and for handling TM matches. Still, these scarce options are based on the traditional input modes comprised of keyboard and mouse. Building on our experience in creating a prototype mobile post-editing interface for smartphones, we have created a translation editing environment that accepts additional input modes, such as touch commands (on devices equipped with touch screens, such as tablets and select laptops) and voice commands – using automatic speech recognition. Another important tool feature is the inclusion of accessibility principles from the outset, with the aim of opening translation editing to professionals with special needs. In particular, the tool is being designed to cater for blind translators. Our presentation will report on initial usability tests with an early version of the tool. The results include productivity measurements as well as data collected using satisfaction reports. Our ultimate goal is to test whether the tool can help alleviate some of the pain points of the edit-intensive, mechanical task of desktop post-editing. |
Dimitra Kalantzi
|
POSTER - MT and post-editing from a translator’s perspective There is no doubt that MT is nowadays one of the major trends in the translation industry. Indeed, more and more translation agencies offer MT and post-editing services to their clients, and professional translators are more and more likely to be offered post-editing tasks in their everyday work. In this context, and drawing from my own experience with MT and post-editing as a translator, I will discuss some common myths around MT and post-editing, will suggest some additional services that both translation agencies and freelance translators can offer in relation to MT, and will also put forward some reservations and ideas regarding MT evaluation within the translation industry. This paper will also make a plea to universities and academics involved in the teaching of MT courses and modules to also cater to the needs of practicing translators. |
Sheila Castilho, Joss Moorkens, Federico Gaspari, Andy Way, Yota Georgakopoulou, Maria Gialama, Vilelmini Sosoni and Rico Sennrich Sheila Castilho is a post-doc researcher in the ADAPT Centre in Dublin City University. Her research interests include human and usability evaluation of machine translation, translation technology and audio-visual translation.
Co-authors
|
Crowdsourcing for NMT Evaluation: Professional Translators versus the Crowd The use of machine translation (MT) has become widespread in many areas, from household users to the translation and localization industries. Recently, the great interest shown in neural machine translation (NMT) models by the research community has made more detailed evaluation of this new paradigm essential, since several comparative studies using human and automatic evaluation of statistical and neural MT have shown that results concerning the improvements of NMT are not yet conclusive (e.g. Castilho et al. 2017). Crowdsourcing has become a frequently-employed option to evaluate MT output. In the field of translation, such crowds may consist of translation professionals, bilingual fans or amateurs, or a combination thereof. Crowdsourcing activities are at the heart of the European-funded research and innovation project TraMOOC (Translation for Massive Open Online Courses). In this presentation, we will focus on the MT evaluation crowdsourcing activities performed by professional translators and amateur crowd contributors. We will present the results of this evaluation based on automated metrics and post-editing effort and compare how translators and the general crowd assessed the quality of the NMT output. |
Jon Riding and Neil Boulton
|
(Stand-by for main track) Learning from Sparse Data - Breaking the Big Data Stranglehold The Bible Societies have for many years built systems to help translators working in scores of languages. Their focus is in linguistic analysis rather than synthesis. But there is a problem, shared by all MT systems. Until there is enough text to train the system the output is limited. By the time there is enough training data much of the task may already be complete. To address this, United Bible Societies has begun to re-imagine what we expect from our translation support systems. A system is now in development which begins learning about the target language at the very start of a Bible translation project. Rather than building stand alone morphology analysers, glossing engines and aligners the project constructs a learning framework within which all of these machines, and more, can operate with very small amounts of text, using outputs from one context to strengthen a hypothesis from another. This paper describes a framework within which such processing might take place, how that framework enables learning to take place from very small amounts of data, how that learning is gradually aggregated into a coherent language model and how this model is used to support the translator in their work.
|
Michael Farrell
Besides this, he is also a freelance translator and transcreator. Over the years, he has acquired experience in the cultural tourism field and in transcreating advertising copy and press releases, chiefly for the promotion of technology products. Being a keen amateur cook, he also translates texts on Italian cuisine.
|
Building a custom machine translation engine as part of a postgraduate university course: a case study In 2015, I was asked to design a postgraduate course on machine translation (MT) and post editing. Following a preliminary theoretical part, the module concentrated on the building and practical use of custom machine translation (CMT) engines. This was a particularly ambitious proposition since it was not certain that students with degrees in languages, translation and interpreting, without particular knowledge of computer science or computational linguistics, would succeed in assembling the necessary corpora and build a CMT engine. This paper looks at how the task was successfully achieved using KantanMT to build the CMT engines and Wordfast Anywhere to convert and align the training data. The course was clearly a success since all students were able to train a working CMT engine and assess its output. The majority agreed their raw CMT engine output was better than Google Translate’s for the kinds of text it was trained for, and better than the raw output (pre-translation) from a translation memory tool. There was some initial scepticism among the students regarding the effective usefulness of MT, but the mood clearly changed at the end of the course with virtually all students agreeing that post-edited MT has a legitimate role to play. |
Claire Lemaire and Christian Boitet
|
POSTER - On the Need of New Computer Aids for Translating Writers Thanks to an experiment in French companies, we found out a new situation of multilingual writing, for which there seems to be no dedicated translation aids. Given the relative lack of competence on the target language (usually but not always English) we propose to build a new kind of CAT tools incorporating interactive (but asynchronous) disambiguation in source at some point during analysis and specific PE aids tuned to the user profiles. The new system would be a DBMT (Dialogue-Based MT) system, that allows the user to edit the source and target texts, during the translation process, instead of translating and then post-editing the target text. The system would use two advantages of this new situation: (1) the expert knowledge of the “translating writers” on their domain, and (2) the possibility for them to change both texts, unlike a regular translator. That approach would solve one of the main problems of MT, namely the poor quality of source texts usually given to the translators. Also, the MT results would be immediately assessed and if the translation is bad, immediately produced again after a change in the source text so that the source text be more machine translatable. |
Silvia Rodríguez Vázquez and Sharon O'Brien
|
POSTER - Web accessibility compliance in localisation: the missing link for an optimal end user experience In an increasingly competitive business landscape, the ever-evolving localisation industry is now striving for differentiation. One of the strategies adopted, particularly by the largest multinationals, has been to expand their service coverage beyond traditional localisation and the provision of translation technology to satisfy new digital market needs. Concretely, we have observed a considerable increase in the number of companies showcasing knowledge and know-how in Digital Marketing and User Experience Design, always with a clear goal: enhancing the final end user experience when interacting with multilingual web content. But are we really ensuring an optimal experience for all? If the localisation industry is looking to consolidate this strengthened service portfolio, awareness of key human-computer interaction aspects and best practices, including web accessibility standards, could be crucial for success. Drawing upon the data collected through a series of interviews with representatives of six world-leading multinational companies from the localisation industry and one of their clients, this paper will report on the readiness of current localisation workflows and professionals to deliver more accessible multilingual websites for all. We will also review the overlaps between responsive design, SEO and current web accessibility guidelines, and present how their compliance could bring competitive advantage to localisation businesses. |
Emmanuelle Esperanca-Rodier, Laurent Besacier and Caroline Rossi
Co-authors
|
Evaluation of NMT and SMT systems : A study on uses and perceptions Statistical and neural approaches have permitted fast improvement in the quality of machine translation, but we are yet to discover how those technologies can best “serve translators and end users of translations” (Kenny, 2017). To address human issues in machine translation, we propose an interdisciplinary approach linking Translation Studies, Natural Language Processing and Philosophy of Cognition. Our collaborative project is a first step in connecting sound knowledge of Machine Translation (MT) systems to a reflection on their implications for the translator. It focuses on the most recent Statistical MT (SMT) and Neural MT (NMT) systems, and their impact on the translator’s activity. BTEC-corpus machine translations, from in-house SMT and NMT systems, are subjected to a comparative quantitative analysis, based on BLEU, TER (Translation Edit Rate) and the modified version of METEOR from the LIG (Servan & al, 2016). Then, we qualitatively analyse translation errors from linguistic criteria (Vilar, 2006) or the MQM (Multidimensional Quality Metrics) using LIG tools, to determine for each MT systems, which syntactic patterns imply translation errors and which error type is mainly made. We finally assess translators’ interactions with the main error types in a short post-editing task, completed by 10 freelance translators and 20 trainees. |
Corey Miller, Danielle Silverman, Vanesa Jurica, Elizabeth Richerson and Rodney Morris Corey Miller is a linguist working at MITRE Corporation in USA. Trained in sociolinguistics and phonetics, he has worked for several years in the speech technology industry. More recently he has been focusing on problems in computer-assisted translation and terminology management, where he hopes to eventually incorporate his interests in sociolinguistics and speech. |
(Stand-by for main track) Enlisting CAT-tools in the battle for register equivalence There seems to be general agreement that aiming for equivalence in register between source and target languages in translation is a good thing; in fact, this is now encoded in translation services standard ISO 17100:2015 as “compliance with any proprietary and/or client style guide (including register and language variants)”. The question this paper will address is what specific things computer-assisted translation (CAT) tools can do to aid in this process. We will discuss the role of both termbases and translation memories (TMs) in recording register information. Finally, we will discuss work on register in machine translation (MT) and how this may ultimately facilitate a register-enabled CAT workflow. It is hoped that this discussion specifying ways in which the CAT workflow can be fortified to accommodate register information will provide researchers and developers a path forward for a forthcoming generation of CAT tools which will make it easier for translators and reviewers to maintain and assess register fidelity. |
Samuel Läubli and David Orrego-Carmona
|
When Google Translate is better than some human colleagues, those people are no longer colleagues Expressing discomfort with machine translation is a recurrent theme in translator forums on social media. We analyse posts from Facebook, LinkedIn, and Twitter, showing that translators spend considerable time and effort on mocking and discussing machine translation failures. Research has shown a disconnect between translation technology researchers and practitioners, while at the same time indicating the benefits of collaboration between them. Reflecting on an analysis of posts and engagement of translators in social media, we outline three suggestions to bridge this gap: (i) identify and report patterns rather than isolated errors, (ii) organise or participate in evaluation campaigns, and (iii) engage in cross-disciplinary discourse. Rather than pointing out each other’s deficiencies, we call for computer scientists, translation scholars, and professional translators to advance translation technology by acting in concert. |
Joss Moorkens Joss Moorkens is a lecturer in Translation Technology in the School of Applied Language and Intercultural Studies in Dublin City University (DCU) and a researcher in the ADAPT Centre and the Centre for Translation and Textual Studies. Within ADAPT, he has contributed to the development of translation tools for both desktop and mobile. He is co-editor of a book on human and machine translation quality and evaluation (due in 2018) and has authored journal articles and book chapters on topics such as translation technology, post-editing of machine translation, human and automatic translation quality evaluation, and ethical issues in translation technology in relation to both machine learning and professional practice. |
(Stand-by for main track) A Survey of Accredited Irish Language Translators Translators are currently facing changes in employment conditions and work practices as the technologised ‘vendor model’ has become commonplace. The situation for Irish language translators is particularly dynamic. Language technology is belatedly making a real impact, fuelled by regulatory compliance needs and the removal of the derogation of Irish as an official language of the EU. This study surveys almost half of the 178 accredited Irish language translators, focusing on their opinions on the role of a translator, use of translation technology, the status of Irish within the EU, and job satisfaction. Their responses contrast the perspectives of freelance and public service translators. Participants in this survey are passionate about translation and about the Irish language, and while some translators appear to be thriving, many are not. Responses show a fear of dropping translation quality, a lack of translation talent, and the lack of an audience for translation. Participants’ perspectives differ based on their conditions of employment, with disparities apparent in ratings of job satisfaction – particularly regarding their sense of purpose and payment terms, and in their expressions of positive or negative prospects for the future of their profession. |
Martin Kappus, Erik Angelone, Romina Schaub-Torsello, Martin Schuler and Maureen Ehrensberger-Dow
Co-authors
Erik Angelone is professor of translation studies at the ZHAW Institute of Translation and Interpreting. His research interests are in process-oriented translator training, translation pedagogy and curricular design, and empirical translation studies.
|
When is less actually more? A usability comparison of two CAT interfaces The body of evidence is growing that CAT tools have fundamentally altered the tasks that most non-literary translators engage in and possibly also their cognitive processing. Recent research suggests that translators may be exposing themselves to unnecessary cognitive friction by the way they use their tools (O’Brien et al. 2017). If tool settings and features do not align with translators’ ways of working, then flow can be interrupted and cognitive load increased. Fatigue and reduced attention are two consequences of cognitive overload over extended periods, both of which have been associated with an increase in errors and lower productivity. We report on a usability comparison of two interfaces for translation work that differ with respect to the information and functions available on the screen when the factory default settings are used (i.e. one interface has several fields with supporting functions visible and the other has a simpler look). Eye tracking measures and indicators from retrospective commentaries and interviews highlight how novices interact with the two interfaces and various features. We consider the implications of our findings in light of recent calls for less cluttered user interfaces and open the discussion of how cognitive load can be reduced. |
Andrzej Zydroń
CTO @ XTM International, Andrzej Zydroń is one of the leading IT experts on Localization and related Open Standards. Zydroń sits/has sat on, the following Open Standard Technical Committees: 1. LISA OSCAR GMX Zydroń has been responsible for the architecture of the essential word and character count GMX-V (Global Information Management Metrics eXchange) standard, as well as the revolutionary xml:tm (XML based text memory) standard which will change the way in which we view and use translation memory. Zydroń is also chair of the OASIS OAXAL (Open Architecture for XML Authoring and Localization) reference architecture technical committee which provides an automated environment for authoring and localization based on Open Standards. Specific areas of specialization: |
Beyond Neural MT A lot of hype and excitement has surrounded the latest advances in Neural Machine Translation (NMT) and generally with some justification: output is generally more fluent and closer to normal human output. Nevertheless some of the claims need to be qualified and practical implementation of NMT is not without difficulty: typically double the training material is required when compared to Statistical Machine Translation (SMT) and training a new engine can take weeks not days. Although NMT can produce much more fluent output than SMT it can have limited impact concerning real world localization tasks. Extensive tests have proven that in the end there is no great improvement in post-editing throughput and NMT is no panacea for omission or mistranslation. With NMT it is also impossible to ‘tune’ the output as can be done with SMT: you have no knowledge of how the NMT engine has made its decisions. Most practical translation projects do not have anywhere near enough training data and do not have the luxury of waiting weeks for an engine to be trained even if there was enough data. If the training has been done on unrelated material or material that is not directly relevant to the customer’s terminology then misleading results can be produced: due to its improved fluency NMT can make identifying mistakes more difficult. NMT quality can also drop with the length of sentences and translating from a morphologically rich language to one that is morphologically impoverished can in fact produce worse results than SMT. |
Marianne Starlander
|
Adapting a Computer Assisted Translation MA Course to New Trends The present paper will present how we adapted our MA CAT tool class to two current trends. The first trend is the drastic rise of the number of students enrolled in the class. We report on the impact of the rise of students by presenting how challenging it has become to give them the assignment described in Starlander et Morado Vazquez (2013) and in Starlander (2015) The discussion is oriented towards how to teach this evaluation methodology in a different way, by adapting the content and most of all the teaching methods (crowdsourcing, online quiz). We describe in detail how these new activities fit into the entire course content. The second trend is the integration of MT into CAT tools. How can we best introduce this evolution in our teaching? We present the main results of a preliminary experience of integrating a translation exercise involving the use of MT. The final discussion is dedicated to more general teaching challenges implied by the ever moving trends in teaching translation technology. |
Claudio Fantinuoli
|
Speech Recognition in the Interpreter Workstation In recent years, computer-assisted interpreting (CAI) programs have been used by professional interpreters to prepare assignments, to organize terminological information, and to share event-related information among colleagues (Fantinuoli, 2016, 2017). One of the key features of such tools is the ability to support users in accessing terminology during simultaneous interpretation (SI). With state-of-the-art CAI tools, interpreters need to manually input a term or part of it in order to query the database. The main drawback to this approach is that from the booth it is considered both time-consuming and, to some extent, distracting during an activity that requires concentration and rapid information processing (Tripepi Winteringham, 2010). However, initial empirical studies on the use of such tools seem to support the idea that interpreters on the job may have the time and the cognitive ability to look up terms. Furthermore, CAI tools seem to contribute to improving terminology and overall interpreting performance (Prandi 2015; Biagini 2016). With this in mind, the automatization of the querying system would represent a step forward in reducing the additional cognitive effort needed to perform this human-machine interaction. With more free cognitive ability at disposal, it is reasonable to assume that a CAI tool equipped with an automatic look up system would contribute to further improving the terminology and overall performance of interpreters during the simultaneous interpretation of specialized texts. Speech Recognition (SR) has been proposed as a methodology and technology to automatize the querying system of CAI tools (Fantinuoli 2016; Hansen-Schirra 2012). In the past, the difficulty to build SR systems that were accurate enough to be useful outside of a carefully controlled environment has hindered its deployment in the interpreting setting. However, recent advances in Artificial Intelligence, especially since the dissemination of deep learning and neural networks, have considerably increased the quality of SR (Yu and Deng, 2015). In order to be successfully integrated in an interpreter workstation, both SR and CAI tools must fulfil a series of specific requirements. For example, SR must be truly speaker-independent, have a short reaction time, and be accurate in the recognition of specialized vocabulary. On the other hand, CAI tools need to overcome some shortcomings of current implementations and need, for instance, to handle morphological variants of the selection of results and new ways to present extracted terminology. In the first part of the paper, a framework for the integration of SR in CAI tools will be defined. In particular, much attention will be devoted to the analysis of state-of-the-art SR and the problems that may arise with its integration into an interpreter workstation. Secondly, the adaptation of traditional querying systems used in CAI tools to allow for keyword spotting will be discussed and a prototype will be presented. Finally, general advantages and shortcomings of SR-CAI integration will be highlighted and prospective developments of the use of SR that support the access of terminological data will be introduced, i.e. the recognition of numbers and entities. |
Chong Zhang and Matteo Capelletti Chong Zhang is a PhD candidate at the Linguistics Department of Stony Brook University |
POSTER - A Case Study of Machine Translation in Financial Sentiment Analysis The Social Sentiment Index (SSIX) project [1] aims at overcoming language barriers and realizing a financial sentiment platform capable of scoring textual data in different languages. Since the cost of multilingual sentiment analysis can be high, our project deploys a relatively low-cost yet sufficient approach to help small-scale companies expand to new markets through analyzing social contents in any languages. Our approach first built a sentiment gold standard (GS) corpus (e.g. English) annotated by human financial domain experts. Then the GS corpus was translated into a target corpus (e.g. German) by three machine translation (MT) engines (Microsoft, Google, and Google Neural Network) integrated into Geofluent [2] to allow pre-/post-processing, such as DO-NOT-TRANSLATE rules to tackle with special financial terms. Our approach takes the maximal advantage of human translation while keeping the cost low by incorporating MT. A crucial prerequisite is that the sentiment of a statement in the GS corpus can be transferred to the target corpus after translation. To meet the prerequisite, we investigate the impact of MT on the sentiment quality of the GS. Experiment 1 A sample of 700 English tweets was selected. It was translated into German simultaneously by one human translator and three MT engines. Then BLEU [3] was calculated to evaluate the quality of the translations. Results suggested that Google and Google Neural Network performed better than Microsoft on 1-gram, and vice versa on the rest. Engine Microsoft Google Google Neural Network 1-gram 2-grams 3-grams 4-grams 0.901470798 0.865873923 0.786125067 0.684824095 0.963509145 0.846959705 0.728174371 0.605465403 0.963340387 0.846025029 0.727096883 0.604167208 For the purpose of SSIX, the quality of translation is considered the best when there is minimal discrepancy in sentiment between the original and the translation. To explore the sentiment preservation, we conducted Experiment 2. Experiment 2 A subset of the sample (N = 200) was selected and three German financial domain experts assigned the translations sentiment scores. The regression analyses were done with the lmer4.0 package in R. We first compared the sentiment of the English GS with the four translations. Results showed that the three MTs had significantly different sentiment from the GS (Microsoft: t = -3.574, p < .001; Google: t = 2.038, p < .05; Google Neural Network: t = 3.101, p < .01), but human translation did not have significantly different sentiment from the GS. Thus we conclude that human translation is the most reliable in sentiment preservation. Then, using human translation as the benchmark, we compared it to MTs. Results showed Microsoft did not preserve the sentiment (t = -2.16, p < 0.05), but both Google and Google Neural Network did (no significant difference). Conclusion Our research provides evidence that sentiment transfer can be successful through MT if using Google and Google Neural Network in Geofluent. This is a crucial step towards achieving a multilingual sentiment platform in the domain of finance. Next, we plan to integrate language-specific processing rules to enhance the performance of MT. |
Bianca Prandi
|
CAI tools in the interpreting booth: a proposal for a theoretical model and research methodology Even though studies on computer-assisted interpreting still represent a very small percentage in the body of research, the topic is starting to gain attention in the interpreting community. So far, only a handful of studies have focused on the use of CAI tools in the interpreting booth (Gacek, 2015; Biagini, 2015; Prandi, 2015a, 2015b). While they did shed some light on the usability and the reception of CAI tools as well as on the terminological quality of simultaneous interpreting performed with the support of such tools, these studies were only product-oriented. We still lack process-oriented, empirical research on computer-aided interpreting. A pilot study currently underway at the University of Mainz/Germersheim (Prandi, 2016, 2017) aims at bridging this gap by combining process- and product-oriented methods. After discussing the theoretical models adopted to date in CAI research, this paper will suggest how an adaptation of Seeber’s (2011) Cognitive Load Model can be better suited then Gile’s (1988, 1997, 1999) Effort Model to operationalize hypotheses on the use of CAI tools in the booth. The paper will then introduce the experimental design adopted in the study with a focus on the features of the texts used and on the rationale behind their creation. |
Bert Wylin and Hendrik Kockaert
|
Building Artificial Intelligence on top of a Translation Waste Mountain The Translation department of the KU Leuven researches the revision and correction of translations. Recently we joined forces with Televic to build our own tools for smart translation revision: we are interested in the “waste”, in the errors that translators make. From a didactical point of view, the analysis of those errors is as interesting as the correct translation. We will show which (game changing) teaching and learning conclusions we can draw from the analysis of the “waste mountain”. TranslationQ and RevisionQ are two tools to evaluate and score translations. Translation evaluation is an important and labour intensive task in the training and in the selection of good translators. Mostly this work is done by human evaluators and has to be repeated for every single translation. Our academic experiments have proven that both tools are as accurate and even more objective than a human evaluation. TranslationQ and RevisionQ are especially useful to evaluate large groups of candidates. Finally, the language correction algorithms have been developed to be language independent, making the tools useable for many language combinations. |
Koen Kerremans and Helene Stengers
Helene Stengers is professor in Spanish proficiency, translation and Interpreting at the department of Linguistics and Literary Studies of Vrije Universiteit Brussel, where she obtained her PhD in 2009. Her research interests lie in applied comparative linguistics (especially English and Spanish), cognitive linguistics, phraseology and Foreign Language acquisition (mainly vocabulary acquisition) from a multilingual and intercultural perspective with a view to optimize Foreign Langage pedagogy, as well as translation and interpreter training. She is the research director of the Brussels Institute for Applied Linguistics. |
POSTER - Using online and/or mobile virtual communication tools in interpreter and translator training: pedagogical advantages and drawbacks In this paper we discuss some preliminary results of a comparative study into the use of online and/or mobile virtual communication tools in the master programmes of interpreting and translation at Vrije Universiteit Brussel. Both master programmes are based on a situated learning model, which is generally understood as a didactic method in which translation and interpreting students learn the profession and acquire professional skills through hands on experience by exposing them to simulated or real work environments, situations and tasks. In recent years, this learning-by-doing approach (or authentic experiential learning) has gained quite some traction in translator and interpreter education. In creating authentic learning contexts for student translators and interpreters, technology has become an important factor to take into consideration, given the unmistakable impact that it has on professional translation and interpreting practices. After a review of previous studies dealing with the use of virtual technologies in translator and interpreter training, several virtual communication tools will be tested and evaluated both from the trainers’ and the trainees’ perspectives. Finally, we will reflect on the tools’ pedagogical advantages and drawbacks in order to formulate recommendations for using these technologies in translator and interpreter training contexts. |
Laura Cacheiro Quintas
|
POSTER - Towards a Hybrid Intralinguistic Subtitling Tool: MIRO Translate Making audiovisual educational material accessible for non-native speakers and people who are deaf or hard-of-hearing is an ongoing challenge and the state-of-the-art in this field shows that no current software provides a fully automatic, high-quality solution. This article presents Miro Translate, a hybrid intralinguistic subtitling tool developed in response to this challenge by the MIRO Programme at the University of Perpignan Via Domitia. This cloud-based solution proposes synergies between machine and human subtitlers to simplify the technical and linguistic tasks of subtitlers. To this end, Miro Translate integrates the automatic speech recognition (ASR) technology provided by the Microsoft Translator Speech API, a deep neural network (DNN) system and TrueText technology to improve speech readability. Auto-generated captions constitute a solution to enhance productivity. Nevertheless, certain subtitling conventions must be considered to provide a readable and legible target output. A set of pre-editing and post-editing functionalities have been identified to assist the machine in the spotting task and to improve the quality of auto-generated captions. In conclusion, Miro Translate constitutes a cost-efficient solution to meet the increasing demand of high quality captions for video lecturers. |
Kristiina Abdallah
|
Three-dimensional quality model: The focal point of workflow management in organisational ergonomics Although quality is a central concept in every act of translating, it has been considered difficult to define and therefore remained elusive. Generally, approaches to quality, both in translation studies and in translation industry, have concentrated on the product and/or process quality. Yet, in the present-day man and machine mediated, collaborative translation production networks, the challenge to define and manage quality comprehensively has become more acute than ever before. This paper participates in the discussion on organizational ergonomics of translation by presenting a three-dimensional quality model. The model encompasses not only the so-far familiar product and process dimensions, but also a third dimension called social quality. Social quality, the focus of this paper, addresses the relations of the actors involved, both human and non-human, and their organizational interaction. The theoretical discussion on quality will be complemented by a recent case from Finland regarding the working conditions of the audio-visual translators of Star Wars: The Force Awakens and their impact on translation quality. By emphasizing the point that quality is a multidimensional concept which also includes social and ethical aspects, the paper argues for workflow management that caters to the needs of people, who are the bedrock of the industry. |
Vincent Vandeghinste, Sven Coppers, Jan Van den Bergh, Tom Vanallemeersch, Els Lefever, Iulianna van der Lek-Ciudin, Kris Luyten and Frieda Steurs
|
SCATE: A Smart Computer-Aided Translation Environment We present SCATE: A Smart Computer-Aided Translation Environment developed in the SCATE research project. It is a carefully designed prototype of the user interface of a translation environment, that displays different translation suggestions coming from different resources in an intelligible and interactive way. Our environment contains carefully designed representations that show relevant context to clarify why certain suggestions are given. In addition, several relationships between the source text and the suggestions are made explicit, to help the user understand how a suggestion can be used and select the most appropriate one. Well designed interaction techniques are included that improve the efficiency of the user interface. The suggestions are generated through different web services, such as translation memory (TM) fuzzy matching, machine translation (MT) and support for terminology. A lookup mechanism highlights terms in the source segment that are available with their translation equivalents in the bilingual glossary. |
Confirmed workshops (updated to 17 August)
David Filip David Filip is Chair (Convener) of OASIS XLIFF OMOS TC; Secretary, Editor and Liaison Officer of OASIS XLIFF TC; a former Co-Chair and Editor for the W3C ITS 2.0 Recommendation; Advisory Editorial Board member for the Multilingual magazine; Co-Chair of the Standards Interest Group at JIAMCATT. His specialties include open standards and process metadata, workflow and meta-workflow automation. David works as a Moravia Fellow at the ADAPT Research Centre, Trinity College Dublin, Ireland. Before 2011, he oversaw key research and change projects for Moravia’s worldwide operations. David held research scholarships at universities in Vienna, Hamburg and Geneva, and graduated in 2004 from Brno University with a PhD in Analytic Philosophy. David also holds master’s degrees in Philosophy, Art History, Theory of Art and German Philology. |
Does your tool support XLIFF 2? This will be a hands on workshop for up to 15 participants. Participants will be required to bring their own laptops and supply their own legally obtained and valid licenses (can be evaluation licenses) of tools whose XLIFF 2 capability they’ll want to verify in the workshop. In the workshop, participants will learn about free and open source tools that can be used to verify XLIFF 2 support in CAT tools AND how to use those tools for that end. The resources employed will be the OASIS XLIFF TC hosted XLIFF 2 test suites, OKAPI XLIFF Toolkit Lynx validation service and command line tool. oXygen XLIFF framework, OASIS hosted XLIFF 2 validation artifacts, FREME Framework XLIFF services, Microsoft XLIFF 2 Object Model, Xmarker validation service etc. This workshop will provide actionable knowledge and skills with regards to validating XLIFF 2 support thus giving the participants the practical ability to verify tool makers’ marketing claims about their XLIFF 2 support. |
Joss Moorkens and Kristiina Abdallah
|
Freelance translation and the computer The profession of translation has moved at a greater pace than many others towards contingent and freelance work. These work practices, coupled with greater use of technology, continue to change the nature of translation work, with associated effects on translator’s agency and autonomy. Following on from our proposed main-track session on agency and work practices in translation production networks, in this workshop we will present a short summary of our work and thoughts on contingent work in translation, highlighting opportunities to maximise agency. The main purpose of this session, however, is to facilitate a discussion about working standards for translators and satisfaction with technology, and the effects of these influences on job satisfaction and translation quality. Related to these are considerations of productivity expectations and income, and whether participants’ experiences with both are realistic and fair. Finally, we wish to consider how translators’s agency and sense of purpose could be maximised in translation production networks. |
Gloria Corpas Pastor
Visiting Professor in Translation Technology at the Research Institute in Information and Language Processing (RIILP) of the University of Wolverhampton, UK (since 2007), and Professor in Translation and Interpreting (2008). Published and cited extensively, member of several international and national editorial and scientific committees. 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 the future ISO Standard (ISO TC37/SC2-WG6 “Translation and Interpreting”). Regular evaluator of University programmes and curriculum design for the Spanish Agency for Quality Assessment and Accreditation (ANECA) and various research funding bodies. President of AIETI (Iberian Association of Translation and Interpreting Studies), member of the Advisory council of EUROPHRAS (European Society of Phraseology) and Vice-President of AMIT-A (Association of Women in Science and Technology of Andalusia). |
VIP: Voice-text integrated system for interpreters Interpreting is an extremely strenuous task, since they must devote much effort in terms of decoding, memorising and encoding a message. Interpreters should, as translators and other language professionals do, benefit from the development of technology and, thereby, enjoy considerable improvement of their working conditions. However, currently their work relies by and large on traditional or manual methods, and the technological advances in interpreting have been extremely slow. Unlike translators, for whom a myriad of computer-assisted tools are available, interpreters have not benefited from the same level of automation or innovation. Fortunately, there is a growing interest in developing tools addressed at interpreters as end users, although the number of these technology tools is still very low and they are not intended to cover all interpreters needs. The goal of the VIP project is to revolutionise the interpreting industry by creating an interpreting workbench tool which will have the same effect that language technologies for translators have had in the translation industry in recent decades. To this end, we intend to (a) identify the |
Anja Rütten
|
Terminology management tools for conference interpreters – Current tools and how they address the specific needs of interpreters Ever since the 1990s, sophisticated terminology management systems have offered a plethora of data fields and management functions to translators, terminologists, and conference interpreters. Nevertheless, interpreter-specific tools have been developed in parallel to suit their special needs. They were mostly inspired, at least initially, by one or very few users and developed by a single developer or a very small team. The intention of this workshop is to give interpreters and other interested participants an overview on which tools are available for their terminology work, highlighting the pros and cons of each of them. Providers and developers of terminology management systems will get valuable insight on the specific needs of conference interpreters and the reasons why, if using terminology management systems at all, conference interpreters tend not to use the sophisticated term databases translators or terminologists use. Due to time restrictions, only the most relevant aspects of terminology management in conference interpreting will be addressed. Which solution is best for filtering and categorising my terminology? Which one offers the best search function for the booth? Which one is best for sharing glossaries and online collaboration, or most convenient for mobile use? Information on price models and supported operating systems will also be provided.
If time allows, generic solutions like Microsoft Excel/Access and Google Sheets will also be discussed as an alternative to interpreter-specific tools. |
Andrzej Zydroń
CTO @ XTM International, Andrzej Zydroń is one of the leading IT experts on Localization and related Open Standards. Zydroń sits/has sat on, the following Open Standard Technical Committees: 1. LISA OSCAR GMX Zydroń has been responsible for the architecture of the essential word and character count GMX-V (Global Information Management Metrics eXchange) standard, as well as the revolutionary xml:tm (XML based text memory) standard which will change the way in which we view and use translation memory. Zydroń is also chair of the OASIS OAXAL (Open Architecture for XML Authoring and Localization) reference architecture technical committee which provides an automated environment for authoring and localization based on Open Standards. Specific areas of specialization: |
The Localization Industry Word Count Standard: GMX-V Word and character counts are the basis of virtually all metrics relating to costs in the L10N Industry. An enduring problem with these metrics has been the lack of consistency between various computer assisted tools (CAT) and translation management systems (TMS). Notwithstanding these inconsistencies there are also issues with common word counts generated by word processing systems such as Microsoft Word. Not only do different CAT and TMS systems generate differing word and character counts, but there is also a complete lack of transparency as to how these counts are arrived at: specifications aren’t published and systems can produce quite widely different metrics. To add clarity, consistency and transparency to the issue of word and character counts the Global Information Management Metrics Volume (GMX-V) standard was created. Starting with version 1.0 and then as version 2.0 GMX-V addresses the problem of counting words and characters in a localization task, and how to exchange such data electronically. This workshop goes through the details of how to identify and count words and characters using a standard canonical form, including documents in Chinese, Japanese and Thai, as well as how to exchange such data between systems. |
Anja Rütten, Alexander Drechsel and Josh Goldsmith
|
PANEL DISCUSSION : New frontiers in interpreting technology Technology has the potential to shape the future of interpreting. Indeed, it has already begun to do so. From tools that assist interpreters to devices that may replace them altogether, technologies for delivering interpreting services to tools to teach interpreting, this panel discussion will span the gamut of technology in interpreting, considering current developments and future innovations. |