Papers by Mathieu Lacroix

    1 papers
    Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms (2025.acl-long)

    Copied to clipboard

    Challenge: Existing methods for sequence labeling are hidden Markov models and conditional random fields (CRF).
    Approach: They propose a new discriminative model for sequence labeling called Bregman conditional random fields (BCRF) they propose to use Fenchel-Young losses to learn from partial labels.
    Outcome: The proposed model performs better in highly constrained settings than the existing model, which is slower and faster.

    What is GenGO?

    GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

    Information

    About
    Limitations