SemiAmor : Amortized Lagrangian Prediction for NLP
ANR CE23-2023-0005

SemiAmor is an ANR-funded project spanning 4 years (2024-2027). It aims to bridge semi-amortized methods developed in probabilistic inference and Lagrangian relaxation for Natural Language Processing

Meetings

Meeting 07/06/24

Finally the finances are sorted out, the project can begin! For our first meeting we discussed:

  1. Joseph Le Roux (PI) summarized the structure of the project.
  2. Francesco Demelas presented some work on the Prediction of Lagrangian Multipliers for MILPs, accepted at ICML24.
  3. Joseph Le Roux presented some preliminary work on Amortization and LR for supervised POS-tagging.
  4. Caio Corro presented some preliminary results on using Bregman divergence for weakly supervised POS tagging.

Emacs 29.4 (Org mode 9.6.15)