Persian Pronoun Resolution: Leveraging Neural Networks and Language Models

TL;DR

This paper introduces the first end-to-end neural network system for Persian pronoun resolution, utilizing Transformer models to jointly detect mentions and resolve antecedents, significantly improving accuracy.

Contribution

It presents a novel neural approach that combines mention detection and antecedent linking for Persian pronoun resolution, outperforming previous rule-based and statistical methods.

Findings

3.37 F1 score improvement over previous state-of-the-art

First end-to-end neural system for Persian pronoun resolution

Effective use of ParsBERT transformer model

Abstract

Coreference resolution, critical for identifying textual entities referencing the same entity, faces challenges in pronoun resolution, particularly identifying pronoun antecedents. Existing methods often treat pronoun resolution as a separate task from mention detection, potentially missing valuable information. This study proposes the first end-to-end neural network system for Persian pronoun resolution, leveraging pre-trained Transformer models like ParsBERT. Our system jointly optimizes both mention detection and antecedent linking, achieving a 3.37 F1 score improvement over the previous state-of-the-art system (which relied on rule-based and statistical methods) on the Mehr corpus. This significant improvement demonstrates the effectiveness of combining neural networks with linguistic models, potentially marking a significant advancement in Persian pronoun resolution and paving the way for further research in this under-explored area.