TRANSLATION TECHNOLOGY e-module

  Feedback form: 

https://docs.google.com/forms/d/e/1FAIpQLSeGniGkxGQSPzPGXHNzduezXb_DZ0Wq8ws3W4-_8zwYSEtiSA/viewform  

Download the entire module:Translation technology e-Module                                                                                                  

In this module you learn about translation technology. The module consists of units and each unit deals with a different aspect of the topic (see table above). At the beginning of each unit you find the learning outcome to be reached after completing the learning activities. You also find information on the learning context, f.i. competences required for the specific content provided in the unit, technical and other requirements and your workload given in minutes. For your orientation an overview of the activities and their main characteristics (title, description, rationale etc.) are also provided. Afterwards you find the activities in a worksheet. At the end a reference for further reading is given.

Please feel free to add your own examples (own activities, best practices, used methods, assessment techniques etc.) to the list of units because not all aspects of quality management could be considered in this module.

Below you will find the module’s structure divided into units and indicating the topic to be dealt with.

Table of contents

UNIT 1: INTRODUCTION TO TRANSLATION PRODUCTIVITY TOOLS. 5

Activity 1 Technology - the extension of human capabilities. 10

Activity 2 Introduction to translation productivity tools. 10

Activity 3 Technology - past and future. 11

UNIT 2: EVALUATION OF TRANSLATION PRODUCTIVITY TOOLS. 12

Activity 1 Which tool to choose?. 17

Activity 2 A translation productivity tool in detail. 17

Activity 3 Workflow of translation productivity tools. 18

UNIT 3: USE OF TRANSLATION PRODUCTIVITY TOOLS. 20

Activity 1 Webinar - CAT tools. 33

Activity 2 Translation request. 34

Activity 3 Translation commentary. 35

Activity 4 Machine translation - evaluation. 36

Activity 5 Comparison of machine translations. 37

Activity 6 Corpus. 37

List of figures. 38

List of references. 38

Didactical background information for trainer

Structure of activities:

individual work / work in small groups → discussion in small groups / whole-class → evaluation in small groups / whole-class → evaluation by trainer

This way learning occurs through: knowledge activation → knowledge extension → knowledge organisation → knowledge assessment.

Attention! We move from knowledge orientation (what) to competence orientation (how) through inquire- based learning.

Inquire-based learning:

• Problem-oriented: real-life problems of future translators are embedded into activities
• Research-based: trainees get as little instructions as possible, knowledge and competence will be acquired through searching (info-mining competence).
• Up-to-date: trainees do not learn to work with one specific tool (tools and their functions get obsolete!) rather they develop a toolkit to evaluate tools.
• Future-oriented: sharpening a sense of staying/keeping informed (e.g. through activities linked to future work – Unit 1, activity 4)
• Fosters critical thinking through questioning, e.g. evaluation method:

1) evaluating according to own criteria (basic)

2) evaluating according to guidelines (complex) – questioning own evaluation criteria

• Includes not only rational but also other aspects of real-life, e.g. emotions like fear/anxiety related to machine translation
• Fosters teamwork through steadily changing group-composition (at the beginning also place for individual study)
• Fosters communication through presentation in different teams and in whole-class
• Fosters communication through guidelines and toolkits (e.g. how to verbalise arguments regarding a translation choice / how to evaluate tools)
• Trainee-centred learning: trainer steps back and has a guiding role.

Transferability:

• Synergies can be transferred with other subjects: through links between modules / working collaboratively across subject boundaries → Cross-curricular working and close cooperation between lecturers are required
• Content and language is replaceable through other topics, languages, e.g. in Unit 3, Activity 2, 4
• Transferable skills are fostered through activities / linking activities to other modules. What has been learnt in one module will be required in another one and vice versa.
• Working with as many group members in peer or in small groups as possible fosters reflection and evaluation by giving feedback and/or receiving it from others
• Connected to professional future: trainees get to know different tools e.g. through evaluation rather than learning to work with one specific tool which will be out-of-date/obsolete when they start work

Evaluation may include presentation in whole-class – trainer extends missing information (presence needed) or collects ideas in white board (distance learning – presence not needed).

In case of simultaneous work (e.g. Unit 2, Activity 2) it is better to use online tools to avoid redundancies.

UNIT 1: INTRODUCTION TO TRANSLATION PRODUCTIVITY TOOLS

Learning context

Overview of learning activities

Background information for trainer: 

Activity 1

Following areas of human abilities/capacities can be enhanced through technology:

• mobility
• interaction
• sociability
• speed,
• memory
• reliability
• consistency
• information processing
• creation of artefacts
• etc.

Rubrics

• distance
• mental capabilities
• cognitive capabilities
• etc.

Activity 2

According to ISO 17100:2015 Translation technologies can include the following:

a) content management systems (CMSs);

b) authoring systems;

c) desktop publishing;

d) word processing software;

e) translation management systems (TMSs);

f) translation memory (TM) tools and computer aided translation (CAT);

g) quality assurance tools;

h) revision tools;

i) localization tools;

j) machine translation (MT);

k) terminology management systems;

l) project management software;

m) speech-to-text recognition software.

Translation technologies can also include other relevant existing and future translation technology.

Bibliography

ISO 17100:2015 Translation services — Requirements for translation services

History of technology applied to translation industry in general

Background for trainees

Trainer will explain the development of technology in the last century and the current one, as well as the way those development has impacted the way translators and project managers work.

Background for trainers

The trainer will explain how the technological evolution has been developed in the previous century with the different waves in computing and how those developments impacted the way translation industry changed.

The appearance of the electric typewriter, the first text processors, the desktop publishing, the CAT systems, the project management systems and machine translation systems are just linear examples of evolution which significantly changed the way translators and companies perform their work.

The trainer will work on the document ‘Technologies for translation’ (Freigang, 2009), where a complete history of translation technology evolution is listed, which a special focus on CAT tools, which set the beginning of the translation technology up today. This document is a starting point for discussion.

In 2008 Zetzche coined the acronym TEnTs for Translation Environment Tools, replacing the older term Translation Workbench or Translation Workstation. In this article Zetzche stated the following:

Mazes of tents? Of course, I am not talking about tents made of fabric, poles, ropes, and pegs. Instead, I am referring to translation environment tools (TEnTs). As the name suggests, these TEnTs provide translators with an environment that allows them to work productively. This environment includes a translation memory and a terminology database, but it also provides features for quality assurance, spell-checking, workflow management, project management, analysis, support for complex file formats, and so forth. Anyone who has even glanced into the market of commercially available TEnTs will know about tools like Trados, Star Transit, Déjà Vu, and across, and it would be hard enough to make a choice among those. However, it becomes exponentially harder when you look more closely and find more than a dozen tools!.

Other authors state similar ideas, such as Alcina (2008: 79): “Translation technologies constitute an important new field of interdisciplinary study lying midway between computer science and translation. Its development in the professional world will largely depend on its academic progress and the effective introduction of translation technologies in the translators training curriculum”.

As an illustration which can serve as a base for discussion, the trainees can comment on this image:

Figure 1 The future according to FIT (EUATC and Hermes Traducciones, 2017)

According to the Trend Report 2018 the future developments may include the following:

• industry will change with cloud-based services, connectivity and big data
• the human brain will be almost fully understood
• the computing power will be able to replicate human brain
• AI will understand cultural context
• ethical, moral and economic implications of AI will be clarified
• the limits of AI will become much clearer
• businesses will be concerned about liability in the absence of human agents
• only minimalist approaches will survive
• CAT-tools’ complexity will be reduced
• ‘intelligent’ user interfaces will be built
• technological results will be improved in background / without making the user learn or operate something new
• more and more solutions will adapt to our preferences 

Bibliography

Alcina, A. (2008): Translation technologies: scope, tools and resouces. https://www.researchgate.net/publication/233657002_Translation_technologies_Scope_tools_and_resources

EUATC and Hermes Traducciones, 2017

Freigang, J. (2009). “Technologies for translation”. http://eventi.dipintra.it/tetra/convegni/tetra_1/allegati/freigang.pdf>. 

Slator: https://slator.com/sponsored-content/important-trends-translation-technology-2018/  

Trend Report 2018 https://memoqtrendreport.com/about/   

Zetzsche, J. (2008). “A Maze of TEnTs”. ATA Chronicle, July 2008. Alexandria: ATA. 47.

WORKSHEET

Activity 1 Technology - the extension of human capabilities

Discuss in small groups (2-3) how technology can extend human capacities in the field of (specialised) translation. List the concrete areas technology affect:

Activity 2 Introduction to translation productivity tools

Brainstorm in your group on the hardware / software professional translators use nowadays. Capture your ideas by creating a mind map. Try to group the tools according to similarities.

Activity 3 Technology - past and future

Individual research: Study the history of technology applied to translation industry in general and the role translators played. Fill in the timeline with information about the main developments and the translator’s role.

Group work: Discuss in small groups (3-4) what will happen in the translation industry in the future. What do you think how would look like your daily business in the future? Complement the timeline’s information boxes with the main result of the discussion.

UNIT 2: EVALUATION OF TRANSLATION PRODUCTIVITY TOOLS

Learning context

Overview of learning activities

Background information for trainer: 

Activity 1

- price vs. free version

- user-friendliness (ease of setup/doing business with, etc.)

- trial

- license duration

- languages supported

- target customer size

- customer review

- support

- webinars / tutorials

- operating systems Web/Installed and Mobile

- compatibility

- interoperability (eg. MemoQ vs. Trados → Plugins)

- system requirements

- features:

• Billing & Invoicing
• Collaboration
• CRM
• For Software
• For Websites
• Localization Automation
• Machine Translation
• Marketing Management
• Order Management
• Permission Management
• Project Tracking
• Quality Control
• Quotes / Estimates
• Resource Management
• Terminology Management
• Translation Analytics
• Translator Database
• Version Control
• Workflow Management

Bibliography

https://www.capterra.com/translation-management-software/compare/162762-151746/memoQ-vs-SDL-Trados-Studio

https://www.g2crowd.com/compare/sdl-trados-studio-vs-memoq-translator-pro

https://www.nimdzi.com/webinar-translation-management-systems-a-comparison/

https://www.proz.com/software-comparison-tool/compare/7-130/memoq-to-SDL%20Trados%20Studio%202019

Activity 2 & 3

Background information for trainees:

Figure 2 The Nimdzi Language Technology Atlas 2018

Choose a (not yet listed) translation productivity tool (e.g. from the Nimdzi Language Technology Atlas 2018) which you would like to describe in depth and indicate its full name and your name in the list.

There are some tools’ comparisons – helping to assess what is best for the business: capterra, g2crowd, etc.

Bibliography

The Nimdzi Language Technology Atlas (2018) https://www.nimdzi.com/language-technology-atlas/

Translation productivity tools

Across https://www.across.net/en/

CafeTran Espresso https://www.cafetran.com/

Déjà Vu http://www.atril.com/

Fluency Now https://www.westernstandard.com/Default.aspx

Gnome https://wiki.gnome.org/

Lilt https://lilt.com/

Lionbridge https://www.lionbridge.com/de-de/translation-workspace

Lokalize https://www.kde.org/applications/development/lokalize/

Madcap https://www.madcapsoftware.com/products/lingo/

MateCat https://www.matecat.com/

maxprograms https://www.maxprograms.com/products/

MemoQ https://www.memoq.com/en/

MemSource https://cloud.memsource.com/

MetaTexis http://www.metatexis.de/

MultiTrans https://www.multitranstms.com/

OCLanguage http://www.oclanguage.com/

OmegaT http://omegat.org/

Pootle http://pootle.translatehouse.org/

SDL http://www.sdl.com/

Smartcat https://www.smartcat.ai/

Smartling https://www.smartling.com/

STAR https://www.star-ts.com/technology/

Systran http://www.systransoft.com/

Terminotix https://terminotix.com/?lang=en

TextUnited https://www.textunited.com/

Verifika https://e-verifika.com/

Virtaal http://virtaal.translatehouse.org/

Wordbee http://www.wordbee.com/

Wordfast http://www.wordfast.com/

XTM Cloud https://xtm-intl.com/

WORKSHEET

Activity 1 Which tool to choose?

Carry out research in order to find out which aspects play a role for or against a specific translation productivity tool in the decision making procedure. Create a list of the aspects by ranking their importance.

Activity 2 A translation productivity tool in detail

Carry out research and describe in detail the translation productivity tool of your choice according to its aspects. At the end summarize its main possibilities and limitations. Present the main results in whole-class!

Activity 3 Workflow of translation productivity tools

Analyse with your peer the figure below (Fig. 2) and compare the tool you described with the translation workflow illustrated. List and describe the workflow activities covered by the chosen tool’s features.

Figure 3: Translation workflow (© ISO17100, 2015)

Share the results of your discussion with the whole group.

UNIT 3: USE OF TRANSLATION PRODUCTIVITY TOOLS

Learning context

Overview of learning activities

Background information for trainer: 

Activity 1

Pym (2012) emphasises the idea of training the trainees to develop their own learning and assessing techniques rather than training them to use specific industry tools which could easily be rendered obsolete by changing circumstances.

In this section trainees are provided with the necessary knowledge and skills to assess any CAT tool from the standpoint of their specific needs.

ISO/IEC 9126-1 (2001) and ISO/IEC 25010 (2011) are used to evaluate software in general.

According to Starlander (2013) in the literature on CAT tool and TM system evaluation, three studies are particularly widely referred to: Höge (2002), Gow (2003) and Rico (2000) showing several ways of interpreting the ISO standards.

Elaborating a prioritized list of context specific requirements and checking if the required features are present in the systems under comparison are discussed in:

Gow 2003

Keller 2011

Zerfass 2002, 2010;

Evaluation of translation aids should be carried out with reference to the needs of a specific user (in this activity newly graduated freelance translator who wants to buy an adequate TM system).

A step by step evaluation method for TM tools is offered by EAGLES (1999):

1. Why is the evaluation being done?

What is the purpose of the evaluation? Do all parties involved have the same understanding of the purpose? What exactly is being evaluated? Is it a system or a system component? A system in isolation or a system in a specific context of use? Where are the boundaries of the system?

2. Elaborate a task model

Identify all relevant roles and agents

What is the system going to be used for?

Who will use it? What will they do with it? What are these people like?

3. Define top level quality characteristics

What features of the system need to be evaluated? Are they all equally important?

4. Produce detailed requirements for the system under evaluation, on the basis of 2 and 3

For each feature which has been identified as important, can a valid and reliable way be found of measuring how the object being evaluated performs with respect to that feature? If not, then the features have to be broken down in a valid way, into sub-attributes which are measurable. This point has to be repeated until a point is reached where the attributes are measurable.

5. Devise the metrics to be applied to the system for the requirements produced under 4.

Both measure and method for obtaining that measure have to be defined for each attribute.

For each measurable attribute, what will count as a good score, a satisfactory score or an unsatisfactory score given the task model (2)? Where are the cut off points?

Usually, an attribute has more than one sub-attributes. How are the values of the different sub-attributes combined to a value for the mother node in order to reflect their relative importance (again given the task model)?

6. Design the execution of the evaluation:

Develop test materials to support the testing of the object.

Who will actually carry out the different measurements? When? In what circumstances? What form will the end result take?

7. Execute the evaluation:

Make measurement.

Compare with the previously determined satisfaction ratings.

Summarize the results in an evaluation report, cf. point 1.

The practical implementation of the following steps can be found in form of a concrete scenario (a translation agency is considering acquiring a terminology management tool, in order to gain better efficiency and consistency in the terminology which they translate) here:

EAGLES (1999) https://www.issco.unige.ch/en/research/projects/eagles/ewg99/7steps.html   

A quicker evaluation method for choosing the most appropriate tool can be found online on nimdzi.

Following TMS types are included:

• Web & Software 
• Middleware
• Machine Translation 
• Business Management 
• Term/memory Banks
• Online Repositories 
• Technical documentation 
• Marketing
• Automation 
• Support 
• Etc.

Bibliography

EAGLES Evaluation Working Group (1999) ‘The EAGLES 7-step recipe’ [online], available: http://www.issco.unige.ch/en/research/projects/eagles/ewg99/7steps.html   

Gow, F. (2003) Metrics for Evaluating Translation Memory Software (M.A.), University of Ottawa.

Höge, M. (2002) Towards a Framework for the Evaluation of Translators' Aids Systems (PhD), Faculty of Arts, Department of Translation Studies, University of Helsinki.

ISO/IEC 9126-1: Software engineering — Product quality — Part 1: Quality model (2001).

ISO/IEC 25010: Systems and software engineering -- Systems and software Quality Requirements and Evaluation (SQuaRE) -- System and software quality models (2011).

Keller, N. (2011) ‘Translation-Memory-Systeme: Neun auf einen Blick’, Mdü, available: http://www.metatexis.org/reviews/TM-Vergleich-MDUE-2011.pdf

https://www.nimdzi.com/tms 

Pym, A. (2012) ‘Translation skill-sets in a machine-translation age’, [online], available: http://usuaris.tinet.cat/apym/on-line/training/2012_competence_pym.pdf

Quah, C. K. (2006) Translation and Technology, Hampshire/New York: Palgrave. Macmilla

Rico, C. (2001) ‘Reproducible models for CAT tools evaluation: A user-oriented perspective’, Proceedings of the Twenty-third International Conference on Translating and the Computer, London. Aslib.

Starlander, M. & Vázquez, L. M. (2013) ‘Training translation students to evaluate CAT tools using Eagles: a case study’ In Aslib: Translating and the Computer 35. Londres (Royaume Uni)

Zerfaβ, A. (2002) ‘Comparing Basic Features of TM Tools’, Multilingual Computing & Technology, 13 (7), 11-14.

Zerfaβ, A. (2010) MemoQ 4, Multilingual Computing & Technology, 21 (4), 14-17.

Activity 2

A possible solution:

Activity 3

Writing translation commentary according to certain methodological guidelines gives trainees the skills to ground strategies in an organised way and to rationalise their own translation process.

Trainees usually do not know how to justify their translation decisions and how to lay the foundations for their arguments in an organised fashion. They usually argue with following statements: “it sounds better”, „I found it in the dictionary”, “I don’t think that’s the way it’s said...”, etc.

According to García Álvarez (2007) following aspects should be considered by writing a translation commentary:

1. Translation instructions of the commission (translation norms, textual norms, etc.)

2. The macro-purpose sought with the TT (possible differences with respect to the macro-purpose of the ST)

3. Ideological, cultural and informative considerations and/or differences between the receptors of the TT and the ST

4. Textual conventions of the TT (norms according to its typology, what it allows and what it doesn’t, differences with those of the ST, etc.)

5. Possible defects in the ST

6. Date and place of TT publication (possible temporal/situational differences with the ST if applicable)

7. Possible problems in expression and any other types of problems bound up with the intentionality of the TT, and possible differences in relation to the intentions of the ST (persuasive, informative, directive, instructive, expressive)

8. Textual structure of the TT in relation to the ST (topic-centred, main act-centred, mixed structure, etc.)

9. Text acts vs. speech acts of both texts (according to the maxims and conventions established by each culture)

10. Functional relations of utterances in both texts (including possible omissions, extensions, paraphrase, etc., and problems related to the specific degree of explication and implication necessary to express the informativity of the TT, keeping in mind the principles of economy and relevance)

11. Terminology: pragmatic-cognitive conceptual similarities and differences between both communicative situations and based on the differences between receptors (exotisation, domestication; prototype semantics; metaphoric, metonymic and image-schematic mappings; scripts; lexical categories according to the translation instructions, etc.)

12. Stylistic issues and problems in the TT (linguistic register, jargon, problems related to field, mode and tone/tenor, etc.)

13. Cohesion in the TT: problems with collocations, punctuation, suprasegmental features, referential relations of form and meaning between sentences, theme-rheme structure, etc.

14. Photos or other non-verbal elements, photo captions and typographical elements in the TT (possible differences with those of the ST)

15. Consulting dictionaries, encyclopaedias, parallel texts, databases, informants, etc.

16. Negotiations with the translation client and other determining factors in the process

17. Time allotted for completing the translation

18. Other considerations (e.g. arguments based on declarative knowledge: translation studies, interdisciplinary theories, etc.)

19. Similarities and differences between both texts (e.g. according to Beaugrande & Dressler’s (1981) seven textuality criteria: situationality, intentionality, acceptability, intertextuality, informativity, coherence and cohesion.

Bibliography

García Álvarez, A. M. (2007) Evaluating Students' Translation Process in Specialised Translation:  Translation Commentary In The Journal of Specialised Translation, 7, 139-163 https://www.jostrans.org/issue07/art_alvarez.php

Activity 4 & 5

Bibliography

https://www.bing.com/translator

https://translate.yandex.com/

https://translate.google.com/?hl=de

Machine translations:

Acivity 5

Short description of SMT, NMT and hybrid systems:

Statistical Machine Translation (SMT) has been the dominant translation paradigm for decades. Although effective, statistical machine translation methods suffered from a narrow focus on the phrases being translated, losing the broader nature of the target text. The hard focus on data-driven approaches also meant that methods may have ignored important syntax distinctions known by linguists.

Neural machine translation (NMT) is the use of neural network models to learn a statistical model for machine translation. Unlike the traditional phrase-based translation system which consists of many small sub-components that are tuned separately, neural machine translation attempts to build and train a single, large neural network that reads a sentence and outputs a correct translation.

Although effective, the neural machine translation systems still suffer some issues, such as scaling to larger vocabularies of words and the slow speed of training the models. There are the current areas of focus for large production neural translation systems, such as the Google system.

A “hybrid” method combines both techniques to create a desired result. The efficacy of each depends on a number of factors, including the languages used and available linguistic resources, or example text.

Comparing errors of both systems according to the Multidimensional Quality Metrics framework (MQM):

- Accuracy (accuracy): Accuracy issues address the relationship of the target text to the source text and can be assessed only by considering this relationship

Issue types: addition, omission, mistranslation, etc.

- Design (design): Design includes issues related to the physical presentation of text, typically in a “rich text” or “markup” environment.

Issue types: formatting, length, mark-up, etc.

- Fluency (fluency): Fluency includes those issues about the linguistic “well-formedness” of the text that can be assessed without regard to whether the text is a translation or not. Most Fluency issues apply equally to source and target texts.

Issue types: cohesion, grammar, inconsistency, etc.

- Internationalization (internationalization): Internationalization covers areas related to the preparation of the source content for subsequent translation or localization.

- Locale convention (locale-convention): Issues in Locale convention relate to the formal compliance of content with locale-specific conventions, such as use of proper number formats. If content is otherwise correctly translated and fluent but violates specific locale expectations (as defined in the translation specifications), it is addressed in this dimension. This dimension does not cover issues related to whether the content itself is appropriate for the locale (these issues are covered under Verity (verity).

- Style (style): Style issues relate to what is commonly known as “Style”, defined both formally (in style guides) and informally (e.g., a “light style” or an “engaging style”). These issues are closely related to Fluency (fluency), but are often treated separately by tools and quality processes and so are grouped as a separate dimension in MQM.

Issue types: unidiomatic, inconsistent style, awkward, etc.

- Terminology (terminology): Terminology issues relate to the use of domain- or organization-specific terminology (i.e., the use of words to relate to specific concepts not considered part of general language).

- Verity (verity): Verity issues relate to the suitability of content for the target locale and audience. They do not relate to fluency or accuracy since content may be fluently written and accurately translated and still be inappropriate for the target locale or audience.

- Compatibility (Deprecated) (compatibility): The Compatibility dimension includes issues taken from legacy metrics that are not considered appropriate for general use in MQM (because they are related to areas not covered by MQM, such as deadlines, software functionality, or physical production). They are included only for compatibility with these older metrics and should not be used for new MQM metrics.

Issue types: completeness, suitability, legal requirements, etc.

- Other (other): This dimension is used for issues which cannot be otherwise classified into a dimension of MQM. In cases where an unforeseen issue can be classified as belonging to a dimension, it should be classified in that dimension under the top level or using a custom issue type.

Bibliography

Aljoscha Burchardt (2017) Comparing Errors: Neural MT vs. Traditional Phrase-based and Rule-based MT https://www.gala-global.org/publications/comparing-errors-neural-mt-vs-traditional-phrase-based-and-rule-based-mt 

Aljoscha Burchardt, Vivien Macketanz, Jon Dehdari, Georg Heigold, Jan-Thorsten Peter and Philip Williams (2017). A Linguistic Evaluation of Rule-based, Phrase-based, and Neural MT Engines. In Proceedings of EAMT 2017, Prague, Czech Republic.

Arle Richard Lommel, Aljoscha Burchardt, Hans Uszkoreit (2014) Multidimensional Quality Metrics (MQM): A Framework for Declaring and Describing Translation Quality Metrics in: Attila Görög, Pilar Sánchez-Gijón (eds.): 3 Tradumàtica: tecnologies de la traducció volume 0 number 12, Pages 455-463

Multidimensional Quality Metrics (MQM): http://www.qt21.eu/mqm-definition/definition-2015-06-16.html

https://machinelearningmastery.com/introduction-neural-machine-translation/

Dean, J. (2016) Google’s neural machine translation system: Bridging the gap between human and machine translation. https://arxiv.org/abs/1609.08144

Neural Machine Translation: How Artificial Intelligence Works When Translating Language (2017):

http://content.lionbridge.com/neural-machine-translation-artificial-intelligence-works-multilingual-communication/

http://daily.unitedlanguagegroup.com/stories/editorials/statistical-vs-neural-machine-translation

Activity 6

Corpora and concordance software provide a tool to facilitate the translation process, giving translators the opportunity to understand the languages involved and to develop their awareness of the relationships between possible equivalents. (Yingying 2018)

Observing

1. linguistic characteristics,
2. typical structures and
3. text-type-specific formulations

in parallel bilingual corpora enables trainees to

1. make better choices about translation transfer types
2. provide explanations for appropriateness of certain solutions to problems
3. deepen their knowledge of language for specific purposes.

Steps:

All texts should be collected from websites and converted to text format .txt with the AntFile Converter software (a freeware tool to convert PDF and Word files into plain text for use in corpus tools like AntConc).

Figure 4 AntFile Converter designed by Laurence Anthony Screenshot

AntConc - a freeware corpus analysis toolkit for concordancing and text analysis could be used for this activity:

Figure 5 AntConc Concordance designed by Laurence Anthony Screenshot

AntConc Concordance http://www.laurenceanthony.net/software/antconc/

AntFile Converter http://www.laurenceanthony.net/software/antfileconverter/

Yingying Ding (2018) Specialized Translation Teaching Strategies: A Corpus-Based Approach World Academy of Science, Engineering and Technology International Journal of Cognitive and Language Sciences Vol:12, No:5

Zanettin, Federico. (2001) “Swimming in words: Corpora, translation, and language learning”, in Learning with Corpora. In G. Aston, Houston, TX: Athelstan, pp. 177-197.

WORKSHEET

Activity 1 Webinar - CAT tools

Take part in the webinar “Getting started with memoQ for translators” or watch its recorded version.

AND

Take part in the webinar “A beginner’s guide to SDL Trados Studio 2017” or watch its recorded version.

Which tool would you use (MemoQ, Trados, something else…) as a future freelance translator? Why? Write a short evaluation about one of the tools according to the guidelines of Starlander & Vázquez (2013).

Discuss the results in small groups (2-3)!

Activity 2 Translation request

A customer needs the following text translated into Hungarian. Follow the workflow (Unit 2 Activity 3) and create the required translation by using appropriate tools.

Activity 3 Translation commentary

What kind of problems did you face? Write a general descriptive translation commentary according to the guideline of García Álvarez (2007). Present and discuss your commentary in whole-class!

Activity 4 Machine translation - evaluation

For the following translation request use ONE of the online available machine translation tools. Evaluate the result according to the Multidimensional Quality Metrics framework!

Activity 5 Comparison of machine translations

Compare the results of your evaluation with two other peers who used another tools! Write down the main possibilities (+) and limitations (-) of the tested tools.

Would you use machine translation tools as a freelance translator? Which one and why?

Present the main results in whole-class!

Activity 6 Corpus

An LSP needs a bilingual (HU and DE) specialized corpus of conference / marketing materials in the field of e-mobility (about 50,000 words altogether). With the help of an appropriate tool compile the corpus.

Can you make use of it for the translations above (activity 2 & 4)? How?

List of figures

Figure 1 The future according to FIT (EUATC and Hermes Traducciones, 2017) 8

Figure 2 The Nimdzi Language Technology Atlas 2018. 14

Figure 3: Translation workflow (© ISO17100, 2015) 19

Figure 4 AntFile Converter designed by Laurence Anthony Screenshot 31

Figure 5 AntConc Concordance designed by Laurence Anthony Screenshot 32

List of references

Abrami, P. C., Bernard, R. M., Borokhovski, E., Waddington, D. I., Wade, C. A., & Persson, T. (2015) Strategies for Teaching Students to Think Critically A Meta-Analysis. Review of Educational Research, 85(2), 275-314.

Abranyi, H. (2016) Translation Environment Tools in Horváth, I. eds. The Modern Translator and Interpreter, 168-182 http://www.eltereader.hu/media/2016/04/HorvathTheModernTranslator.pdf

Alcina, A. (2008): Translation technologies: scope, tools and resouces. https://www.researchgate.net/publication/233657002_Translation_technologies_Scope_tools_and_resources

Aljoscha Burchardt (2017) Comparing Errors: Neural MT vs. Traditional Phrase-based and Rule-based MT https://www.gala-global.org/publications/comparing-errors-neural-mt-vs-traditional-phrase-based-and-rule-based-mt 

Aljoscha Burchardt, Vivien Macketanz, Jon Dehdari, Georg Heigold, Jan-Thorsten Peter and Philip Williams (2017). A Linguistic Evaluation of Rule-based, Phrase-based, and Neural MT Engines. In Proceedings of EAMT 2017, Prague, Czech Republic.

Arle Richard Lommel, Aljoscha Burchardt, Hans Uszkoreit (2014) Multidimensional Quality Metrics (MQM): A Framework for Declaring and Describing Translation Quality Metrics in: Attila Görög, Pilar Sánchez-Gijón (eds.): 3 Tradumàtica: tecnologies de la traducció volume 0 number 12, Pages 455-463

Biau, G., J. R. (2006) ‘Teaching electronic tools for translators online’, in Pym, A., Perekrestenko, A. and Starink, B., eds., Translation Technology and its Teaching (with much mention of localization), Tarragona: Intercultural Studies Group, Universitat Rovira i Virgili, 86-95.

Biau, G., J. R. & Pym, A (2006) Technology and translation (pedagogical overview) in Pym, A., Perekrestenko, A. and Starink, B., eds., Translation Technology and its Teaching (with much mention of localization), Tarragona: Intercultural Studies Group, Universitat Rovira i Virgili, 5-19.

Dean, J. (2016) Google’s neural machine translation system: Bridging the gap between human and machine translation. https://arxiv.org/abs/1609.08144

Doherty, S., & Moorkens, J. (2013) ‘Investigating the experience of translation technology labs: pedagogical implications’. The Journal of Specialised Translation, 19, 122–136.

Doherty, S. (2016) The Impact of Translation Technologies on the Process and Product of Translation In: International Journal of Communication 10, 947–969

Doherty, S., & Moorkens, J. (2013) ‘Investigating the experience of translation technology labs: pedagogical implications’. The Journal of Specialised Translation, 19, 122–136.

FEMTI (2003) ‘FEMTI - a Framework for the Evaluation of Machine Translation in ISLE’: http://www.isi.edu/natural-language/mteval/

EAGLES Evaluation Working Group (1999) ‘The EAGLES 7-step recipe’ [online], available: http://www.issco.unige.ch/en/research/projects/eagles/ewg99/7steps.html  

EUATC and Hermes Traducciones, 2017

Fernández-Parra, M. (2009) The Workflow of Computer-Assisted Translation Tools in Specialised Translation in Reconceptualizing LSP: Online proceedings of the XVII European LSP Symposium

Freigang, J. (2009). “Technologies for translation”. http://eventi.dipintra.it/tetra/convegni/tetra_1/allegati/freigang.pdf>. 

García Álvarez, A. M. (2007) Evaluating Students' Translation Process in Specialised Translation:  Translation Commentary In The Journal of Specialised Translation, 7, 139-163 https://www.jostrans.org/issue07/art_alvarez.php

Gow, F. (2003) Metrics for Evaluating Translation Memory Software (M.A.), University of Ottawa.

Guillardeau, S. (2009) Freie Translation Memory Systeme für die Übersetzungspraxis: Ein kritischer Vergleich. Masterthesis: http://www.omegat.org/resources/DA_Guillardeau.pdf

Hagen, J. (2011) Ein funktioneller Vergleich: trados und memoQ. Masterthesis: http://othes.univie.ac.at/17506/1/2011-12-12_0515217.pdf

ISO 17100:2015 Translation services — Requirements for translation services

ISO/IEC 25010: Systems and software engineering -- Systems and software Quality Requirements and Evaluation (SQuaRE) -- System and software quality models (2011).

ISO/IEC 9126-1: Software engineering — Product quality — Part 1: Quality model (2001).

ISLE Project (2007) ‘International Standards for Language Engineering, Evaluation Working Group’: http://www.issco.unige.ch/en/research/projects/isle/ewg.html 

Jaatinen, H., & Jääskeläinen, R. (2006). ‘Introducing IT in translator training: Experiences from the COLC project’, in Pym, A., Perekrestenko, A. and Starink, B., eds., Translation Technology and its Teaching (with much mention of localization), Tarragona: Intercultural Studies Group, Universitat Rovira i Virgili, 83-88.

Keller, N. (2011) ‘Translation-Memory-Systeme: Neun auf einen Blick’, Mdü: http://www.metatexis.org/reviews/TM-Vergleich-MDUE-2011.pdf 

Morin, D., Thomas, J. D. E., & Saadé, R. G.(2015) Fostering problem-solving in a virtual environment. Journal of Information Technology Education: Research, 14, 339-362.

Muegge, U. (2013) ‘Teaching computer-assisted translation in the 21st century’, in Ende, A., Herlod, S and Weilandt, eds., Alles hängt mit allem zusammen: Translatologische Interdependenzen. Festschrift für Peter A. Schmitt, Berlin: Frank & Timme, 137-146.

Multidimensional Quality Metrics (MQM): http://www.qt21.eu/mqm-definition/definition-2015-06-16.html

Neural Machine Translation: How Artificial Intelligence Works When Translating Language (2017):

http://content.lionbridge.com/neural-machine-translation-artificial-intelligence-works-multilingual-communication/

Pitar, M. (2016) The Impact of New Technologies on Specialised Translation In: Dejica, D., Hansen, G., Sandrini, P., Para, I. eds. Language in the digital era: Challenges and Perspectives. Berlin: De Gruyter, 60-70.

Popovic, A. (2012) Wie nützlich sind Translation-Memory-Systeme bei der Übersetzung von Fachtexten? Masterthesis: http://othes.univie.ac.at/23538/1/2012-10-25_0606424.pdf

Pym, A., Perekrestenko, A. and Starink, B., eds., Translation Technology and its Teaching (with much mention of localization), Tarragona: Intercultural Studies Group, Universitat Rovira i Virgili.

Pym, A. & Torres-Simón, E. (2015) Designing a course in Translation Studies to respond to students’ questions, In The Interpreter and Translator Trainer, 10/2, 183-203.

Pym, A. (2006) ‘Asymmetries in the teaching of translation technology’, in Pym, A., Perekrestenko, A. and Starink, B., eds., Translation Technology and its Teaching (with much mention of localization), Tarragona: Intercultural Studies Group, Universitat Rovira i Virgili, 113-124.

Pym, A. (2012) ‘Translation skill-sets in a machine-translation age’: http://usuaris.tinet.cat/apym/on-line/training/2012_competence_pym.pdf

Quah, C. K. (2006) Translation and Technology, Hampshire/New York: Palgrave. Macmillan.

Rico, C. (2001) ‘Reproducible models for CAT tools evaluation: A user-oriented perspective’, Proceedings of the Twenty-third International Conference on Translating and the Computer, London. Aslib.

Slator: https://slator.com/sponsored-content/important-trends-translation-technology-2018/ 

Starlander, M. & Vázquez, L. M. (2013) ‘Training translation students to evaluate CAT tools using Eagles: a case study’ In Aslib: Translating and the Computer 35. Londres (Royaume Uni)

The Nimdzi Language Technology Atlas (2018) https://www.nimdzi.com/language-technology-atlas/

Trend Report 2018 https://memoqtrendreport.com/about/    

Yingying Ding (2018) Specialized Translation Teaching Strategies: A Corpus-Based Approach World Academy of Science, Engineering and Technology International Journal of Cognitive and Language Sciences Vol:12, No:5

Zanettin,Federico. (2001) “Swimming in words: Corpora, translation, and language learning”, in Learning with Corpora. In G. Aston, Houston, TX: Athelstan, pp. 177-197.

Zerfaβ, A. (2002) ‘Comparing Basic Features of TM Tools’, Multilingual Computing & Technology, 13 (7), 11-14.

Zerfaβ, . (2010) MemoQ 4, Multilingual Computing & Technology, 21 (4), 14-17.

Zetzsche, J. (2008). “A Maze of TEnTs”. ATA Chronicle, July 2008. Alexandria: ATA. 47.

Links                            

http://daily.unitedlanguagegroup.com/stories/editorials/statistical-vs-neural-machine-translation

http://docs.translatehouse.org/projects/translate-toolkit/en/latest/formats/

http://www.dicits.com/en/technologie/faq/wie-funktionieren-tm-systeme.html

http://www.metatexis.org/reviews/TM-Vergleich_Version_300805.pdf

http://www.sdltrados.com/solutions/translation-memory/

http://www.staff.uni-mainz.de/rumpel/TMS-ILS-0503/TMS-PL/tms-de/

http://www.universitas.org/uploads/media/Universitas_115_web.pdf

http://www.universitas.org/uploads/media/Universitas_215_web.pdf

http://www.universitas.org/uploads/media/Universitas_315_web.pdf

https://machinelearningmastery.com/introduction-neural-machine-translation/

https://translate.google.com/?hl=de

https://translate.yandex.com/

https://www.bing.com/translator

https://www.capterra.com/translation-management-software/compare/162762-151746/memoQ-vs-SDL-Trados-Studio

https://www.g2crowd.com/compare/sdl-trados-studio-vs-memoq-translator-pro

https://www.nimdzi.com/tms 

https://www.nimdzi.com/webinar-translation-management-systems-a-comparison/

https://www.proz.com/software-comparison-tool/compare/7-130/memoq-to-SDL%20Trados%20Studio%202019

Translation productivity tools

Across https://www.across.net/en/

AntConc Concordance http://www.laurenceanthony.net/software/antconc/

AntFile Converter http://www.laurenceanthony.net/software/antfileconverter/

CafeTran Espresso https://www.cafetran.com/

Déjà Vu http://www.atril.com/

Fluency Now https://www.westernstandard.com/Default.aspx

Gnome https://wiki.gnome.org/

Lilt https://lilt.com/

Lionbridge https://www.lionbridge.com/de-de/translation-workspace

Lokalize https://www.kde.org/applications/development/lokalize/

Madcap https://www.madcapsoftware.com/products/lingo/

MateCat https://www.matecat.com/

maxprograms https://www.maxprograms.com/products/

MemoQ https://www.memoq.com/en/

MemSource https://cloud.memsource.com/

MetaTexis http://www.metatexis.de/

MultiTrans https://www.multitranstms.com/

OCLanguage http://www.oclanguage.com/

OmegaT http://omegat.org/

Pootle http://pootle.translatehouse.org/

SDL http://www.sdl.com/

Smartcat https://www.smartcat.ai/

Smartling https://www.smartling.com/

STAR https://www.star-ts.com/technology/

Systran http://www.systransoft.com/

Terminotix https://terminotix.com/?lang=en

TextUnited https://www.textunited.com/

Verifika https://e-verifika.com/

Virtaal http://virtaal.translatehouse.org/

Wordbee http://www.wordbee.com/

Wordfast http://www.wordfast.com/

XTM Cloud https://xtm-intl.com/