Few-Shot Self-Rationalization with Natural Language Prompts

Understand

Self-rationalization models that predict task labels and generate free-text elaborations for their predictions could enable more intuitive interaction with NLP systems.

• These models are, however, currently trained with a large amount of human-written free-text explanations for each task which hinders their broader usage.
• We propose to study a more realistic setting of self-rationalization using few training examples.
• We present FEB -- a standardized collection of four existing English-language datasets and associated metrics.