LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution
Abstract
LingMess, a novel coreference model, uses category-specific pairwise scorers to improve coreference resolution across various datasets.
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 and 5 additional datasets. Our model is available in https://github.com/shon-otmazgin/lingmess-coref
Models citing this paper 2
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 5
Collections including this paper 0
No Collection including this paper