The First Workshop on Human-Informed Translation and Interpreting Technology (HiT-IT)

organised on the 7th Sept 2017 in conjunction with RANLP 2017

Human translation and Machine Translation (MT) aim to solve the same problem (i.e. translating from one language into another) in two seemingly different ways. There are many Natural Language Processing (NLP)/Computational linguistics efforts towards improving the work of translators and interpreters (for example  Computer-Assisted Translation (CAT) tools, electronic dictionaries, concordancers, spell-checkers, terminological databases and terminology extraction tools, translation memories, partial machine translation of template documents, speech recognition systems for automatic subtitling, etc.). In turn, the NLP field makes use of the work and knowledge of professional translators and interpreters in achieving its automatic translation goals – e.g. using parallel aligned text and speech corpora for text and speech machine translation learning, human evaluators of machine translation output, human annotations for automatic MT post-editing or eye-tracking learning of professional translators eye-movements, etc.

While there have been many workshops and conferences representing both sides (machine translation in NLP (e.g. WMT, EAMT conferences), and automatic tools for translators and interpreters in translation/interpreting studies (e.g. Translating and The Computer, and the MT Summit conferences), there hasn’t been an unified workshop which collects the contributions of both fields towards each other.

This workshop addresses BOTH the most recent developments in contributions of NLP to translation/interpreting and the contributions of translation/interpreting to NLP/MT. In this way it addresses the interests of researchers & specialists in both areas and their joint collaborations, aiming for example to improve their own tasks with the techniques & knowledge of the other field or to help the development of the other field with their own techniques & knowledge.

Topics

Submissions are invited on the following and similar topics:

  • NLP approaches & systems for building educational tools & resources for interpreters
  • NLP approaches & systems for building educational tools & resources for translators
  • Translation/interpreting tools, such as translation memories, machine translation
  • Translation/Interpreting resources, such as corpora, terminological databases, dictionaries
  • User requirements for interpreting and translation tools
  • Methodologies for collecting user requirements
  • Human accuracy metrics and human evaluation of machine translation
  • Theoretical papers with translators/interpreters views on how machine translation should work/what output should produce
  • Pre-editing and post-editing of machine translation
  • Human-in-the-loop in automatic generation of inter-lingual subtitles
  • Theoretical papers and practical applications on applying translators techniques & knowledge to NLP and machine translation
  • Theoretical papers and practical applications on applying interpreters techniques & knowledge to NLP and machine translation
  • Human-in-the-loop in automatic generation of inter-lingual subtitles

Given the focus of the workshop, submitted papers should underline their interdisciplinarity and how they gain insights/make contributions from one field to another (human vs automatic translation/interpreting).

Researchers and practitioners in the two fields are invited to submit full papers describing original completed research, short papers presenting ongoing research ideas and demos of working systems. Both theoretical ideas and practical applications are welcome.