University of Edinburgh logo

Philip Williams

I am a research associate in the Institute for Language, Cognition and Computation, where I have been working in the field of machine translation since 2009. My main research interests include multilingual translation and the use of linguistic annotation for machine translation.

email address: pwillia the digit four at inf dot ed dot a c dot u k

Current Projects

  • ELITR - European Live Translator (EU Horizon 2020 Research and Innovation Programme, Grant Agreement No 825460).

Software and Data

Software and datasets that I've either led the development of or made significant contributions to:
  • OPUS-100, a massively multilingual corpus derived from OPUS. Used for the experiments in Zhang et al, (2020).
  • WMT17 Transformer Scripts, scripts for training Transformer models in Nematus.
  • Nematus, a toolkit for neural machine translation, written in Python and Tensorflow.
  • Moses, a toolkit for statistical machine translation, written in C++.
  • taco (no longer supported), a toolkit for working with unification-based constraints in SMT. This software was developed for my thesis and was used in Williams and Koehn (2011), Williams and Koehn (2014), Williams et al. (2014).

Tutorials and Talks