Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech
Recent studies have exploited advanced generative language models to generate Natural Language Explanations (NLE) for why a certain text could be hateful. We propose the Chain of Explanation (CoE) Prompting method, using the heuristic words and target group, to generate high-quality NLE for implicit hate speech. We improved the BLUE score from 44.0 to 62.3 for NLE generation by providing accurate target information. We then evaluate the quality of generated NLE using various automatic metrics and human annotations of informativeness and clarity scores.
PDF Abstract
Datasets
Implicit Hate
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
Adafactor •
Adam •
Attention Dropout •
BART •
BPE •
Cosine Annealing •
Dense Connections •
Discriminative Fine-Tuning •
Dropout •
GELU •
GLU •
GPT-2 •
GPT-Neo •
Inverse Square Root Schedule •
Layer Normalization •
Linear Layer •
Linear Warmup With Cosine Annealing •
Multi-Head Attention •
Residual Connection •
Scaled Dot-Product Attention •
SentencePiece •
Softmax •
T5 •
Weight Decay
