Patrick Fernandes Profile picture
Student Researcher @Google / PhD Student @LTIatCMU & @istecnico. Previously research @Microsoft & @Unbabel
May 3, 2022 14 tweets 7 min read
Tired of beam search and all the heuristics needed to make it work well in MT?
In our work accepted at #NAACL2022 (co-lead @tozefarinhas) we explore an alternative decoding method that leverages neural metrics to produce better translations!

1/14 Image The most common method to obtain translations from a trained MT model is to approximately compute the *maximum-a-posteriori* (MAP) translation with algorithms like beam search

However many works have questioned the utility of likelihood as a proxy for translation quality.

2/14 Image
Apr 25, 2022 14 tweets 7 min read
Trying to interpret your neural networks but out-of-the-box methods aren't working?
In our new preprint, we propose a framework for automatically learning to explain NN decisions!

co-led @MarcosTreviso, w/ @danish037 @andre_t_martins @gneubig

1/14 While many works propose methods for extracting explanations from neural networks, the interpretability community is still trying to figure out what explanations are supposed to *achieve* and how to *evaluate* them.