CLLGAug 22, 2020

HinglishNLP: Fine-tuned Language Models for Hinglish Sentiment Detection

arXiv:2008.09820v18 citations
AI Analysis

This work addresses sentiment analysis for under-explored code-mixed social media text, though it appears incremental as it primarily benchmarks existing methods without introducing new techniques.

The paper tackled sentiment detection in Hinglish (Hindi-English code-mixed) social media text by benchmarking fine-tuned transformer models against classical machine learning methods, finding that an NB-SVM model outperformed RoBERTa by 6.2% relative F1 and a majority-vote ensemble achieved the best F1 of 0.707.

Sentiment analysis for code-mixed social media text continues to be an under-explored area. This work adds two common approaches: fine-tuning large transformer models and sample efficient methods like ULMFiT. Prior work demonstrates the efficacy of classical ML methods for polarity detection. Fine-tuned general-purpose language representation models, such as those of the BERT family are benchmarked along with classical machine learning and ensemble methods. We show that NB-SVM beats RoBERTa by 6.2% (relative) F1. The best performing model is a majority-vote ensemble which achieves an F1 of 0.707. The leaderboard submission was made under the codalab username nirantk, with F1 of 0.689.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes