Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

On Importance of Code-Mixed Embeddings for Hate Speech Identification

Shruti Jagdale, Omkar Khade, Gauri Takalikar, Mihir Inamdar, Raviraj Joshi

TL;DR

HingBERT models, benefiting from training on the extensive Hindi-English dataset L3Cube-HingCorpus, outperform BERT models when tested on hate speech text datasets and code-mixed Hing-FastText performs better than standard English FastText and vanilla BERT models.

Abstract

Code-mixing is the practice of using two or more languages in a single sentence, which often occurs in multilingual communities such as India where people commonly speak multiple languages. Classic NLP tools, trained on monolingual data, face challenges when dealing with code-mixed data. Extracting meaningful information from sentences containing multiple languages becomes difficult, particularly in tasks like hate speech detection, due to linguistic variation, cultural nuances, and data sparsity. To address this, we aim to analyze the significance of code-mixed embeddings and evaluate the performance of BERT and HingBERT models (trained on a Hindi-English corpus) in hate speech detection. Our study demonstrates that HingBERT models, benefiting from training on the extensive Hindi-English dataset L3Cube-HingCorpus, outperform BERT models when tested on hate speech text datasets. We also found that code-mixed Hing-FastText performs better than standard English FastText and vanilla BERT models.

On Importance of Code-Mixed Embeddings for Hate Speech Identification

TL;DR

HingBERT models, benefiting from training on the extensive Hindi-English dataset L3Cube-HingCorpus, outperform BERT models when tested on hate speech text datasets and code-mixed Hing-FastText performs better than standard English FastText and vanilla BERT models.

Abstract

Code-mixing is the practice of using two or more languages in a single sentence, which often occurs in multilingual communities such as India where people commonly speak multiple languages. Classic NLP tools, trained on monolingual data, face challenges when dealing with code-mixed data. Extracting meaningful information from sentences containing multiple languages becomes difficult, particularly in tasks like hate speech detection, due to linguistic variation, cultural nuances, and data sparsity. To address this, we aim to analyze the significance of code-mixed embeddings and evaluate the performance of BERT and HingBERT models (trained on a Hindi-English corpus) in hate speech detection. Our study demonstrates that HingBERT models, benefiting from training on the extensive Hindi-English dataset L3Cube-HingCorpus, outperform BERT models when tested on hate speech text datasets. We also found that code-mixed Hing-FastText performs better than standard English FastText and vanilla BERT models.

Paper Structure

This paper contains 16 sections, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Word Embedding Models
  3. BERT-Base
  4. Multilingual BERT (mBERT)
  5. FastText Embedding Models
  6. L3Cube-HingCorpus and Hing Models
  7. Hing Models vs. BERT models
  8. Hing FastText vs. vanilla FastText
  9. Literature Survey
  10. Methodology
  11. Datasets
  12. Preprocessing
  13. Word Embedding Generation
  14. Classification Algorithms
  15. Results
  16. ...and 1 more sections

Figures (3)

  • Figure 1: Flowchart
  • Figure 2: Comparison Chart for HASOC dataset
  • Figure 3: Comparison Chart for HATE dataset