MeisterMorxrc at SemEval-2020 Task 9: Fine-Tune Bert and Multitask Learning for Sentiment Analysis of Code-Mixed Tweets

TL;DR

This paper describes how the team fine-tuned BERT and used multitask learning to improve sentiment analysis of code-mixed tweets in the SemEval-2020 competition, achieving an F1 score of 0.730.

Contribution

The paper introduces a preprocessing pipeline and a fine-tuning approach with BERT and multitask learning for code-mixed sentiment analysis, achieving top-tier results.

Findings

Achieved an F1 score of 0.730 on the task.

Preprocessing steps improved model performance.

Fine-tuning BERT with multitask learning enhanced sentiment classification.

Abstract

Natural language processing (NLP) has been applied to various fields including text classification and sentiment analysis. In the shared task of sentiment analysis of code-mixed tweets, which is a part of the SemEval-2020 competition~\cite{patwa2020sentimix}, we preprocess datasets by replacing emoji and deleting uncommon characters and so on, and then fine-tune the Bidirectional Encoder Representation from Transformers(BERT) to perform the best. After exhausting top3 submissions, Our team MeisterMorxrc achieves an averaged F1 score of 0.730 in this task, and and our codalab username is MeisterMorxrc.