UoB at SemEval-2020 Task 12: Boosting BERT with Corpus Level Information

TL;DR

This paper demonstrates that incorporating corpus-level TF-IDF information into BERT significantly enhances its performance on social media abuse detection tasks, achieving competitive results in SemEval-2020.

Contribution

The study introduces a method to integrate corpus-level TF-IDF with BERT, improving abuse detection accuracy in social media analysis.

Findings

Significant performance improvement with TF-IDF integration

Achieved near-top results in abuse detection sub-task

Ranked 4th out of 44 teams in target detection

Abstract

Pre-trained language model word representation, such as BERT, have been extremely successful in several Natural Language Processing tasks significantly improving on the state-of-the-art. This can largely be attributed to their ability to better capture semantic information contained within a sentence. Several tasks, however, can benefit from information available at a corpus level, such as Term Frequency-Inverse Document Frequency (TF-IDF). In this work we test the effectiveness of integrating this information with BERT on the task of identifying abuse on social media and show that integrating this information with BERT does indeed significantly improve performance. We participate in Sub-Task A (abuse detection) wherein we achieve a score within two points of the top performing team and in Sub-Task B (target detection) wherein we are ranked 4 of the 44 participating teams.