Post-editing machine translation output
Machine translation (MT) is rapidly becoming a viable technology for an increasing number of language pairs, text types and specialised domains. This practical hands-on workshop explains how professional translators, editors, revisers, localisation specialists, project managers and language service providers working with English can use post-editing (PE) of MT output to increase their productivity while maintaining high quality standards. Special emphasis is placed on the differences between the skills required to successfully revise the work of junior translators and those that are vital to effectively correct MT output without undermining the final quality of the translation.
Developer and facilitator:
Participants in this workshop will
become familiar with the principles of effective PE for the output of different types of MT software (especially statistical and neural systems)
learn to evaluate when and how to carry out PE, depending on the quality of the raw MT output
develop an awareness of the most challenging phenomena for MT systems that are likely to require PE interventions, especially when working with English as either the source or target language (in particular in combination with Italian, as this will be the language pair used in the practical tasks and exercises)
acquire key PE techniques to boost productivity, without compromising on the final translation quality
The workshop will cover the following main topics:
differences between revising human translations and post-editing MT output
various types and levels of PE interventions based on translation quality needs and expectations
how to estimate the advantages of performing PE of raw MT output, depending on quality requirements
effective PE techniques to boost productivity
The workshop will combine theoretical and methodological explanations by the presenter with practical hands-on sessions in which the audience will be actively involved. It is offered to a limited number of participants, who will use their laptops for some practical guided PE tasks and exercises that will be discussed and evaluated together. The workshop will be conducted in English, with examples of MT output and PE exercises focusing on the English<>Italian language pair.
Who should attend?
In-house and freelance professional translators, editors, revisers, localisation specialists, project managers and language service providers working with English, who have an interest in understanding more about MT and especially how PE can help to increase their productivity.
The participants will learn some of the key PE techniques to maximise their productivity as a prerequisite to successfully integrating MT and PE in their translation workflows and multilingual documentation production processes.
This practical hands-on workshop is designed for language and translation professionals who
are willing to learn practical techniques of MT PE to maximise their productivity
have English as one of their working languages (source or target), ideally in combination with Italian – desirable, but not essential
ideally have some experience with technical/specialised translation – desirable, but not essential
ideally are familiar with computer-assisted translation tools (in particular translation memory software) – desirable, but not essential
Participants will need a laptop to carry out the practical exercises.
About the facilitator: Federico Gaspari
teaches English linguistics and translation studies at the University for Foreigners “Dante Alighieri” of Reggio Calabria and is a post-doctoral researcher at Dublin City University, where he works on European research projects focusing on machine translation evaluation. He earned a PhD in machine translation from the University of Manchester and has held lecturing positions at the Universities of Manchester, Salford, Bologna at Forlì and Macerata. His teaching and research interests include translation technologies (especially machine translation evaluation and post-editing), technical and specialised translation, and corpus linguistics. He is a regular presenter at international conferences on these topics.