LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution

2022/05/25 by Otmazgin, Shon, Cattan, Arie, Goldberg, Yoav · 4 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2205.12644

Abstract

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

Cited by

• Gnowsis: Multimodal multitask learning for oral proficiency assessments
• Efficient Seq2seq Coreference Resolution Using Entity Representations
• Mahānāma: A Unique Testbed for Literary Entity Discovery and Linking
• BOOKCOREF: Coreference Resolution at Book Scale

Related

• CorefInst: Leveraging LLMs for Multilingual Coreference Resolution
• Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?
• Findings of the Shared Task on Multilingual Coreference Resolution
• Are Large Language Models Robust Coreference Resolvers?
• ÚFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution