LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution
Shon Otmazgin, Arie Cattan, Yoav Goldberg · 2023
Current state-of-the-art coreference systems are based on a single pairwise scoring component, which assigns to each pair of mention spans a score reflecting their tendency to corefer to each other.We observe that different kinds of mention pairs require different information sources to assess their score.We present LINGMESS, a linguistically motivated categorization of mention-pairs into 6 types of coreference decisions and learn a dedicated trainable scoring function for each category.This significantly improves the accuracy of the pairwise scorer as well as of the overall coreference performance on the English Ontonotes coreference corpus and 5 additional datasets.1