Skip to main content

Metrics for Translation Quality Assessment: A Case for Standardising Error Typologies

  • Chapter
  • First Online:
Translation Quality Assessment

Part of the book series: Machine Translation: Technologies and Applications ((MATRA,volume 1))

Abstract

Translation quality assessment (TQA) has suffered from a lack of standard methods. Starting in 2012, the Multidimensional Quality Metrics (MQM) and Dynamic Quality Framework (DQF) projects independently began to address the need for such shared methods. In 2014 these approaches were integrated, centring on a shared error typology (the “DQF/MQM Error Typology”) that brought them together. This approach to quality evaluation provides a common vocabulary to describe and categorise translation errors and to create translation quality metrics that tie translation quality to specifications. This approach is currently (as of 2018) in the standardisation process at ASTM International and has seen significant uptake in industry, research, and academia. By bringing together disparate strands of quality assessment into a unified systematic framework, it offers a way to escape the inconsistency and subjectivity that have so far characterised TQA.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 139.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 179.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 179.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    http://qt21.eu/mqm-definition/

  2. 2.

    https://www.taus.net/knowledgebase/index.php?title=Error_typology

  3. 3.

    Because most of this chapter is written from the perspective of the author, who was active in development of MQM and the MQM/DQF harmonisation effort – and who had previously led development of the LISA QA Model – much of the account contained here does not cite published sources. For details of MQM and DQF, please see the relevant online resources cited herein.

  4. 4.

    See Popović in this volume for a discussion of the application of MQM to MT.

  5. 5.

    This committee draft in ISO TC37 was subsequently withdrawn and bears no relationship to the current ISO 14080, a standard for management of greenhouse gases.

  6. 6.

    See http://www.qt21.eu/mqm-definition/mqm-spec-2014-02-14.html#hierarchical_list for a full list.

  7. 7.

    See http://www.qt21.eu/mqm-definition/issues-list-2015-05-27.html

  8. 8.

    This total does not include the “Compatibility” branch, which is used only to represent project-related issues from the LISA QA Model, and “Other,” which is used for anything that does not fit into other branches.

  9. 9.

    The full hierarchy and list of issues is available at http://www.qt21.eu/mqm-definition/issues-list.html

  10. 10.

    ASTM International is a leading organisation in the development and delivery of voluntary consensus standards; its Committee F43 on Language Services and Products was formed in 2010 with the aim of enhancing the quality of language services and products.

References

  • ASTM (2014) ASTM F2575–14 standard guide for quality assurance in translation. ASTM International, West Conshohocken

    Google Scholar 

  • Nord C (1997) Translating as a purposeful activity. St. Jerome, Manchester

    Google Scholar 

  • Sirena D (2004) Mission impossible: improve quality, time and speed at the same time. Globalization Insider 13(2.2). Available via: http://www.translationdirectory.com/article387.htm. Accessed 1 Feb 2017

  • Snow T (2015) Establishing the viability of the multidimensional quality metrics framework. Dissertation, Brigham Young University. Available via: http://scholarsarchive.byu.edu/etd/5593/. Accessed 1 Feb 2017

Download references

Acknowledgements

The author thanks the following individuals: Drs. Hans Uszkoreit and Aljoscha Burchardt (DFKI Berlin), who were integral in the development of MQM; Jaap van der Meer and Attila Görög (TAUS), for their development of DQF and contribution to the integrated MQM/DQF metric; Prof. Alan K. Melby (Brigham Young University Translation Research Group), who contributed greatly to MQM and introduced the notion of specifications. Any errors in this publication are the author’s alone and do not reflect on the contributions of these individuals.

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer International Publishing AG, part of Springer Nature

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Lommel, A. (2018). Metrics for Translation Quality Assessment: A Case for Standardising Error Typologies. In: Moorkens, J., Castilho, S., Gaspari, F., Doherty, S. (eds) Translation Quality Assessment. Machine Translation: Technologies and Applications, vol 1. Springer, Cham. https://doi.org/10.1007/978-3-319-91241-7_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-91241-7_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-91240-0

  • Online ISBN: 978-3-319-91241-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics