Ask a Question

Prefer a chat interface with context about you and your work?

Rationalizing Neural Predictions

Rationalizing Neural Predictions

Prediction without justification has limited applicability.As a remedy, we learn to extract pieces of input text as justifications -rationales -that are tailored to be short and coherent, yet sufficient for making the same prediction.Our approach combines two modular components, generator and encoder, which are trained to operate well together.The generator …