Work

LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution

Year: 2023

Type: conference-paper

Abstract: 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

Source: Conference of the European Chapter of the Association for Computational Linguistics

DOI: 10.18653/v1/2023.eacl-main.202

Authors: Shon Otmazgin, Arie Cattan, Yoav Goldberg

Institutions: Bar-Ilan University, Allen Institute for Artificial Intelligence

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: European Commission, H2020 European Research Council

Awards: Information Extraction for Everyone, G434337789