Hopeful_Men@LT-EDI-EACL2021: Hope Speech Detection Using Indic Transliteration and Transformers
This work addresses the problem of identifying hope speech in social media for content moderation, but it is incremental as it applies existing transformer methods to a new dataset.
The paper tackled hope speech detection in multiple languages by comparing contextual embeddings with a majority voting ensemble of fine-tuned transformer models, achieving weighted F1 scores of 0.93 for English, 0.75 for Malayalam, and 0.49 for Tamil, with top rankings in English.
This paper aims to describe the approach we used to detect hope speech in the HopeEDI dataset. We experimented with two approaches. In the first approach, we used contextual embeddings to train classifiers using logistic regression, random forest, SVM, and LSTM based models.The second approach involved using a majority voting ensemble of 11 models which were obtained by fine-tuning pre-trained transformer models (BERT, ALBERT, RoBERTa, IndicBERT) after adding an output layer. We found that the second approach was superior for English, Tamil and Malayalam. Our solution got a weighted F1 score of 0.93, 0.75 and 0.49 for English,Malayalam and Tamil respectively. Our solution ranked first in English, eighth in Malayalam and eleventh in Tamil.