FinMT 2017

Second Finnish Workshop on Machine Translation

Invited keynotes by

The goal of this workshop is to bring together people with interest in machine translation for morphologically-rich languages and Finnish in particular. Morphological complexity and word order freedom are difficult challenges in current MT models and we would like to accelerate the development of systems that can handle languages like Finnish in a more appropriate way especially as the target language. We hope that this event will create new ideas and fosters collaborations leading to substantial improvements in MT for such languages. The following topics are of special interest for the workshop:

  • Neural MT for morphologically-rich languages
  • Tools and resources for Finnish (and other morphologically-rich languages)
  • MT for low-resource languages
  • Evaluation of highly-inflecting languages
  • Long-distance dependencies even across sentence boundaries

Participation is free but requires registration.

Tentative Program

  • 09:15 Coffee & Welcome
  • 09:30 Rico Sennrich: “Neural Machine Translation: What’s linguistics got to do with it?”
  • 10:10 coffee
  • 10:40 – 12:00 Short presentations
    • Robert Östling: “Bilingual word embeddings in NMT”
    • Jenna Kanerva: “Finding translation pairs from unordered internet text”
    • Mark Fishel: “Learning to Translate from Monolingual Data”
    • Maarit Koponen: “Post-editing with different MT models”
  • 12:00 Lunch
  • 13:30 Arianna Bisazza: “Is morphology captured by state-of-the-art neural models of language and translation?”
  • 14:10 – 15:10 Short Presentations
    • Tommi Pirinen: “Workflows for Developing Finnish–German Shallow RBMT with language learning / annotation approach”
    • Raivis Skadiņš (Tilde): “Multilingual and morphology-aware NMT”
    • Lingsoft: MT in the translation industry
  • 15:10 Coffee
  • 15:50 Ondřej Bojar: “Catching the Falling Knife of NMT”
  • 16:30 Wrap-up discussions – Where do we go from here?
  • drinks & dinner …

Local Information