Hate Speech Recognition in multilingual text: Hinglish Documents

Abstract

In this paper, we apply and evaluate several machine learning and deep learning methods, along with various feature extraction and word-embedding techniques, on a consolidated dataset of 20600 instances, for hate speech detection from tweets and comments in Hinglish. The experimental results reveal that deep learning models perform better than machine learning models in general. Among the deep learning models, the CNN-BiLSTM model with word2vec word embedding provides the best results. The model yields 0.876 accuracy, 0.830 precision, 0.840 recall and 0.835 F1-score. These results surpass the recent state-of-art approaches.

Exploration of Whisper fine-tuning strategies for low-resource ASR

“…However, among the more than 7000 languages globally, the majority do not have sufficient training resources like the major languages such as English. According to statistics, about 40% of languages are facing extinction, with a user base of fewer than 1000 users [8][9][10]. It is the scarcity of the transcribed data for these low-resource language communities that prevents large neural networks from being substantially trained, leading to poor performance and a lack of real-world applications.…”