LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution

05/25/2022

∙

by   Shon Otmazgin, et al.

∙

0

∙

share

While coreference resolution typically involves various linguistic challenges, recent models are based on a single pairwise scorer for all types of pairs. We present LingMess, a new coreference model that defines different categories of coreference cases and optimize multiple pairwise scorers, where each scorer learns a specific set of linguistic challenges. Our model substantially improves pairwise scores for most categories and outperforms cluster-level performance on Ontonotes. Our model is available in https://github.com/shon-otmazgin/lingmess-coref