Ferhan Ture, Douglas W. Oard, and Philip Resnik
NAACL 2012
PDF

The list of discussed topics follows the outline of the paper:

• Is the approach of Ture et al. conceptually different from Carpuat 2009?
  • Yes: the decoder just gets additional features, but the decision is up to it – Carpuat 2009 just post-edits the outputs and substitutes the most likely variant everywhere
    • Using Carpuat 2009's approach directly in the decoder would influence neighboring words through LM, so even using this in the decoder and not as post-editing leads to a different outcome
• Human translators and one sense per discourse
  • This suggests that modelling human translators is the same as modelling one sense per discourse – this is suspicious
    • The authors do not state their evidence clearly.
    • One sense is not the same as one translation