Neural Coreference Resolution for Arabic

TL;DR

This paper introduces the first neural coreference resolution system specifically for Arabic, leveraging BERT and an external mention detector, achieving significant performance improvements over previous methods.

Contribution

It presents the first Arabic-specific neural coreference resolver based on Lee et al.'s architecture, combining BERT and mention detection, surpassing existing state-of-the-art results.

Findings

Outperforms previous methods by 15.2 points on OntoNotes 5.0 conll F1

First neural coreference system tailored for Arabic

Identifies current limitations and future directions for Arabic coreference resolution

Abstract

No neural coreference resolver for Arabic exists, in fact we are not aware of any learning-based coreference resolver for Arabic since (Bjorkelund and Kuhn, 2014). In this paper, we introduce a coreference resolution system for Arabic based on Lee et al's end to end architecture combined with the Arabic version of bert and an external mention detector. As far as we know, this is the first neural coreference resolution system aimed specifically to Arabic, and it substantially outperforms the existing state of the art on OntoNotes 5.0 with a gain of 15.2 points conll F1. We also discuss the current limitations of the task for Arabic and possible approaches that can tackle these challenges.