AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Hindi-English Hate Speech Detection: Author Profiling, Debiasing, and Practical Perspectives

Shivang Chopra, Ramit Sawhney, Puneet Mathur, Rajiv Ratn Shah

AAAI 2020 · Large language models › Language, safety and interpretability · approach: Text generation and evaluation metrics · 60 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DeepWalk graph embeddings to CNN+BiLSTM+Attn (ablation)seq2seq CNN+BiLSTM+Attn · HSaccuracy: 0.62 -> 0.71Improved
use DeepWalk instead of node2vec embeddings (ablation)seq2seq CNN+BiLSTM+Attn · HSF1: 0.63 -> 0.67Improved
add node2vec embeddings (ablation)seq2seq CNN+BiLSTM+Attn · HSF1: 0.62 -> 0.63Improved
add profanity vector on top of DeepWalk (ablation)seq2seq CNN+BiLSTM+Attn+DW · HSF1: 0.67 -> 0.73Improved
add DeepWalk graph embeddings to fine-tuned model (ablation)FT CNN+BiLSTM+Attn+PV · HSF1: 0.57 -> 0.64Improved
add bias elimination (ablation)FT CNN+BiLSTM+Attn+PV+DW · HSF1: 0.64 -> 0.73Improved
add bias elimination (ablation)FT CNN+BiLSTM+Attn+PV · HSF1: 0.57 -> 0.64Improved
add bias elimination (ablation)FT CNN+BiLSTM+Attn+PV · HEOTaccuracy: 0.82 -> 0.85+Improved
use CNN+BiLSTM+Attn instead of plain seq2seq+CNN backbone (ablation)seq2seq text model · HSF1: 0.49 -> 0.62Improved
fine-tune word2vec instead of seq2seq translation preprocessing (with PV)CNN+BiLSTM+Attn+PV · HSF1: 0.64 -> 0.57Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy