phase4/README.md

Phase 4 - Many-to-One LSTM and Split-Data Hybrids

Back to model card | Dataset repository

Download this phase report: PDF | Word (.docx)

Setup

• Goal: add a many-to-one LSTM baseline across embeddings and re-run the BiLSTM hybrids on consistent split data.
• LSTM config: embedding_dim 100, hidden_dim 128, dropout 0.2, max_seq_len 100, Adam lr 1e-2, 30 epochs, batch 16. Embeddings: Word2Vec, GloVe, FastText.

Results (many-to-one LSTM, regular training)

Model	Accuracy	F1	AUC-ROC
GloVe+LSTM	0.6779	0.5644	0.7532
Word2Vec+LSTM	0.6675	0.5892	0.7294
FastText+LSTM	0.6610	0.5729	0.7208

Findings

• The plain many-to-one LSTM underperforms the BiLSTM hybrids by ~0.07 to 0.10 F1, confirming the value of bidirectional context for code-mixed text.
• High specificity but low recall: the LSTM variants lean toward the majority (non-hate) class.

Files

• Notebooks: notebooks/ - many_to_one_lstm, ManytooneLSTM
• Figures: figures/ - per-language accuracy curves
• Tables: tables/ - master_metrics, metrics
• Models: models/ - combined/english/hindi/hinglish BiLSTM