Improving Products and Processes in Translation Technology Use (IMPETUS)

Lead Research Organisation: University of Bristol
Department Name: School of Modern Languages


Recent annual figures show that language services are a US$46-billion industry with high growth forecasts. Technology is crucial for coping with demand in this sector. In many contexts, translators now edit and interact with machine translation (i.e. systems akin to Google Translate) instead of translating texts from scratch. The productivity benefits of using machine translation in this way are well known, but the process is controversial and far from smooth. Attitudes to machine translation among language professionals are famously negative. In the press, translators are said to 'have the blues' (The Economist 2017) and to be 'concerned' (El Pais 2017) about the impact of machine translation on their jobs and work. Methods for training translators to use technology are often ineffective, and knowledge of how machine translation affects translators' linguistic decisions is still limited, which poses obstacles to a beneficial use of machine translation in professional workflows. This project is a joint effort to address these issues and improve products and processes linked to translators' interaction with technology. We will examine the efficacy of different working methods and assess new training approaches that can be deployed in the translation workplace. In a context of heated debates on the impact of automation on human labour, our aim is ultimately to empower translators to adopt machine translation in more effective and rewarding ways that can improve their job satisfaction, raise professional standards and boost the multilingual economy.

The project will have three phases. In the first phase, we will investigate the use of neural machine translation, a new paradigm in machine translation technology, and assess different strategies that translators can adopt to improve their work. The second phase will delve deeper into links between translating behaviour and the quality of translated texts. We will examine these links across languages in the largest-scale study to date to establish a connection between what translators do and the quality of the texts they produce. In an innovative integration of research methods and business practices, the third phase of the project will examine how tools that track translators' activity (e.g. edits and translating speed) can be used positively and responsibly in the workplace. We will monitor translators' activity for four months to shed new light on issues such as data ethics and perceptions of productivity as well as on the practical implications of incorporating methods from the project's initial phases into commercial contexts.

Throughout the project, we will use a unique combination of methodologies including objective and subjective techniques. The work is novel in several ways. First, it will provide best-practice documentation on the use of activity tracking in commercial settings and on key editing procedures so far ignored by industry standards and guidelines. Second, with a diverse team of researchers and industry partners, the project constitutes a rare collaboration between translators, academics, technology developers, translation businesses and professional bodies. Our work is rooted in problems reported by and discussed directly with our professional partners. Finally, we will veer away from previous initiatives focused predominantly on the development of new tools to represent a much-needed investment in know-how and capacity building. To date, translators' concerns about the profession have not necessarily aligned with top-down investments in technology that often disregard the technology users, with potentially negative consequences for the technology developers and for translators' professional standing. We hope to change this by concentrating on the human aspects of technological progress and providing empirical evidence on new ways of working and the efficacy of different professional practices.

Planned Impact

Who will benefit from the research?

1. Professional translators

2. Translation company owners and managers

3. Developers of translation technology and of translation technology training

4. Translation students and trainers

How will they benefit from the research?

1. The Institute of Translation and Interpreting (ITI), a globally renowned professional association for translators, is one of the project's partners (see letter of support). The project findings will be shared with ITI's Research Network and disseminated among ITI members through co-produced outputs and events. This will influence translators' approach to technology. They will be able to adopt new ways of working based on these discussions, for example by using tracking tools to gain awareness of their processes. The process of achieving these changes is already in motion through interviews carried out in preparation for the project (see Case for Support). A report on the interviews is available on ITI's website, where the University of Bristol has a dedicated space ( The project will involve independent professionals and address issues of major societal concern. An anonymous translator who attended a sold-out knowledge exchange event to discuss the interview findings mentioned on the exit form that the event was 'comforting for his/her MT [machine translation] fears'. Another one stated that it provided 'a possible way forward'. The event was rated 4/4 by most of those who completed the form.

2. Following new and updated information on best professional practices, translation companies will be able to improve their business strategy. The preliminary interviews indicated a misalignment between many complaints of the participating companies and some of their most frequent practices. Translation production issues mentioned by managers often concerned how translators approached translation tasks (e.g. where they over-edited the text). However, when asked about how they were attempting to tackle these problems, the companies often reported standard error-counting techniques that do nothing to improve translators' approach. The project will allow process-related problems to be addressed based on empirical evidence. Tatutrad (Partner 2 - a translation company in Spain) will be on the front-line of some of these initiatives. To ensure a wider application of the findings, we will be sponsors of a major industry event and exploit our sponsor status to invite other businesses to test our recommendations and report to us on their impact.

3. Technology developers will be able to enhance their products based on the project findings. SDL Plc (Partner 1 - a major provider of language services, technology and training) will benefit from the project first-hand by being able to: (a) update online machine translation post-editing certification tests; (b) fine-tune their tools and machine translation systems based on empirical results reflecting translators' behaviour; and (c) provide their clients with evidence-based information on products and practices.

4. Students and trainers of translation, including those affiliated to the over 550 institutions who participate in SDL's academic programme, will benefit from the research by making use of training materials reflecting empirically sound information on translating behaviour and state-of-the-art technology. The PI has contributed to a 'training the trainers' e-book that SDL currently distributes to universities. The project findings will feed into this documentation and into teaching practices. Just within the project team, these initiatives will reach three countries and institutions (University of Bristol, Kent State University and Universidad Pablo de Olavide). They will be disseminated further, for example through SDL's academic programme and through our participation in major events attended by the academic community.


10 25 50
Description This project has had several outputs. Some of these are currently under review and others have been published. Key findings reported in outputs that have already been published are associated mainly with Phase III of the project, which examined how productivity tracking tools affect professional translators.
The work conducted in Phase 3 of the award involved 16 professional translators based in five different countries. The translators used productivity-tracking tools to monitor their own work for four months. They reported to us weekly during this period, and we also interviewed them at the end of the process. Our key findings include:

(1) Initially some translators felt they could work faster by monitoring their progress, but these positive effects of productivity tracking were in most cases short-lived - translators tended to become demotivated when they did not meet personal targets;
(2) They found the data difficult to interpret, which compromised positive uses translators themselves could make of it;
(3) If behavioural tracking is externally imposed on translators in ways that do not give them control over the data and the process of recording it, this practice has detrimental effects for morale and for translator autonomy;
(4) When behavioural tracking is externally controlled by clients in ways that influence translators' compensation, the data can be used to enforce a paradigm of productivity based on clients' profits, not translators'. For freelance translators, productivity is about their earning power, which is not necessarily synonymous with maximising words/time throughput for a given hourly rate. While the emphasis on words/time productivity is not new in the language services industry, we found that behavioural tracking can exacerbate the precarious nature of some translation jobs by propagating clients' paradigm of productivity at scale under a disguise of algorithmic objectivity. Commercial cloud-based platforms are the loci where these negative effects of behavioural tracking are most likely to be felt.

These findings have been presented at academic and non-academic events. They were published in a peer-reviewed journal article, and other aspects of the data will appear shortly in an industry-oriented report. Based on these results, we call for more awareness of the consequences of tracking translation behaviour. We argue that in most commercial contexts client-controlled productivity tracking and translator autonomy are not compatible.

We draw a distinction, however, between commercial uses of behavioural tracking and uses of this technology that serve research purposes, for example in Translation Process Research. Methods like key-logging and eye tracking have been used for years in academic research. These methods have helped to significantly advance the understanding of the translation process based on studies that take place with translators' informed consent and under the auspices of research ethics committees. We hope that research undertaken in these conditions continues to evolve, and the project's outcomes include contributions in this respect. We have published a program that can be used to process translation activity files generated by the Qualitivity tool for Trados Studio, a plugin that gives translators control over how the data is recorded. Data that translators provide with this tool can now also be processed as part of the data analysis steps of the CRITT (Center for Research and Innovation in Translation and Translation Technology) Translation Process Research Database, which includes a module (Trados2Translog) that can be used to convert Qualitivity outputs to the Translog input format required by CRITT. These tools will serve to improve the ecological validity of translation process research as they allow research tasks to take place in a computer-assisted translation environment that is familiar to translators.

Other project outcomes are currently active and will be recorded here as they become available.
Exploitation Route Outcomes of this funding can be taken forward by professional translators, translation companies, translation technology developers, and academic researchers. All these parties can work together to avoid the detrimental effects of behavioural tracking by strengthening consent procedures and giving translators more information about whether their behaviour is recorded, how, and for what purposes. There is also room to improve existing productivity tools in ways that allow their benefits to be felt by freelance translators. This involves making data outputs more straightforward to use and interpret, and giving translators more control over whether and how the outputs are generated whilst guarding against potential privacy issues and the other negative effects of behavioural tracking outlined above.
Sectors Digital/Communication/Information Technologies (including Software)


Description The project has generated academic impact through improved software and methodologies (see Key Findings, Research Tools and Methods, and Software and Technical Products). Findings from the project have also started to have an impact on non-academic audiences by changing how the research participants themselves (professional translators) approach the use of translation activity tracking. After four months of using productivity tools as part of the project, translators became more experienced with these tools and their implications. They have described the experience as 'eye-opening', and some of them became more aware of their own levels of profitability across time. These translators will be well-placed to avoid detrimental uses of these tools in the future either by avoiding unfavorable behaviour-based pricing schemes or by speaking to different language industry stakeholders about the problems associated with commercial uses of behavioural data. In 2022, findings from the project led to a further funding award from the University of Bristol's ESRC Impact Acceleration Account (IAA). This ESRC IAA Impact Project involved a face-to-face translation productivity workshop that addressed mainly students at Universidad Pablo de Olavide in Seville. It also involved a series of three online workshops addressing professional translators. The online series, titled Translator Profitability Workshops, were organised by the University of Bristol. Across workshops, the series had 50 attendees. Some of them were present at more than one event. The first and last workshops stemmed directly from results of the IMPETUS project. The first was delivered by a professional translator based on her use of the project findings. The last was a summary of the project followed by a roundtable. Participants commented on how they were more aware of the issues raised and welcomed the impact the project was having on debates around key professional practices. Recordings of the events are available here: Further impacts from the projects will be recorded here as they arise.
First Year Of Impact 2020
Sector Digital/Communication/Information Technologies (including Software),Other
Impact Types Societal

Description Impact Acceleration Account 2019: Bristol
Amount £1,405,300 (GBP)
Funding ID ES/T501840/1 
Organisation Economic and Social Research Council 
Sector Public
Country United Kingdom
Start 02/2019 
End 03/2023
Title Trados2Translog 
Description Researchers who collect language translation data with the Qualitivity plugin for Trados Studio will now be able to convert the Qualitivity data into the Translog XML format, which can be processed within the data analysis framework of the Translation Process Research Database of the Center for Research in Translation and Translation Technology (CRITT TPR DB). 
Type Of Material Improvements to research infrastructure 
Year Produced 2020 
Provided To Others? Yes  
Impact This is a very recent resource. In the context of the present award, it has been used to convert the project data collected with Qualitivity, which we analysed in a paper that is under review. The new conversion process has also been used as part of a data collection process linked to Phase 2 of the award, which is now almost complete. Beyond the present award, the tool is being used in a PhD project at Kent State University. Many other projects are expected to benefit from this tool in the near future. 
Title Machine-Assisted Literary Translation 
Description This deposit contains data for two studies where English-to-Chinese translators used neural machine translation (MT) to translate science fiction short stories in Trados Studio. One of the studies (t-p) compares post-editing to a 'no MT' condition. The other (segmentation) examines two ways of presenting the texts on screen for post-editing, namely by segmenting them into paragraphs or into sentences. The dataset is licensed under a Creative Commons "CC BY-NC-SA 2.5" license. 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
Impact Improved understanding of machine-assisted literary translation for the English-Chinese language pair. 
Title Qualitivity Plugin 
Description This is a plugin that is available for the computer-assisted translation tool Trados Studio. The plugin already existed before the award, but a number of improvements to the code were carried out through activities connected to the present award. 
Type Of Technology New/Improved Technique/Technology 
Year Produced 2019 
Impact The data generated by the plugin now includes a new attribute (position) which records the position of the cursor during language translation tasks in Trados Studio. This allowed the development of a new research tool that converts data generated with this plugin. 
Title ilrt/translation-xml-to-cvs: v1.0 first public release 
Description First public release of the software. 
Type Of Technology Software 
Year Produced 2021 
Open Source License? Yes  
Impact So far the software has only been used in relation to this award. It will be used more widely in Translation Process Research in the months and years to come. 
Description Cursos de Verano Olavide en Carmona (Summer School event on translation productivity) 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Undergraduate students
Results and Impact This was a workshop organised by Universidad Pablo de Olavide in Seville. It included eight sessions delivered by a mixture of academics and professional practitioners. The sessions are available online through the URL below.
Year(s) Of Engagement Activity 2022
Description ITI Research Network Event 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact This is an event organised annually by the Research Network of the Institute of Translation and Interpreting, a world-renowned professional association for translators and one of the project partners. Dr Valentina Ragni, a Research Associate in the present award, presented findings from Phase 3 of the project at the event, which was attended by translators and translation researchers.
Year(s) Of Engagement Activity 2020
Description Productivity Tools for Professional Translators 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Professional Practitioners
Results and Impact Workshop on productivity and related tools in the translation industry. Open to members of the WRG (Western Regional Group) of the ITI (the UK Institute of Translation and Interpreting).
Year(s) Of Engagement Activity 2019
Description Translator Profitability Workshops 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact This was a series of three online events. Across the three events, the series had a total of 50 attendees, most of whom professional translators. The events raised awareness and stimulated discussion around key issues concerning translators' productivity, their earning power, and the ethics of some productivity tracking practices undertaken in some professional settings.
Year(s) Of Engagement Activity 2022,2023