Improving Persian Relation Extraction Models by Data Augmentation

TL;DR

This paper enhances Persian relation extraction by augmenting the PERLEX dataset with preprocessing and data augmentation, leading to improved model performance using ParsBERT and multilingual BERT.

Contribution

It introduces an augmented Persian relation extraction dataset and demonstrates improved model performance with data augmentation techniques.

Findings

Achieved 64.67% Macro-F1 in the shared task

Improved generalization and robustness of models

Enhanced PERLEX dataset with augmentation techniques

Abstract

Relation extraction that is the task of predicting semantic relation type between entities in a sentence or document is an important task in natural language processing. Although there are many researches and datasets for English, Persian suffers from sufficient researches and comprehensive datasets. The only available Persian dataset for this task is PERLEX, which is a Persian expert-translated version of the SemEval-2010-Task-8 dataset. In this paper, we present our augmented dataset and the results and findings of our system, participated in the Persian relation Extraction shared task of NSURL 2021 workshop. We use PERLEX as the base dataset and enhance it by applying some text preprocessing steps and by increasing its size via data augmentation techniques to improve the generalization and robustness of applied models. We then employ two different models including ParsBERT and multilingual BERT for relation extraction on the augmented PERLEX dataset. Our best model obtained 64.67% of Macro-F1 on the test phase of the contest and it achieved 83.68% of Macro-F1 on the test set of PERLEX.