Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning

Understand

Complex question-answering (CQA) involves answering complex natural-language questions on a knowledge base (KB).

• However, the conventional neural program induction (NPI) approach exhibits uneven performance when the questions have different types, harboring inherently different characteristics, e.g., difficulty level.
• This paper proposes a meta-reinforcement learning approach to program induction in CQA to tackle the potential distributional bias in questions.
• Our method quickly and effectively adapts the meta-learned programmer to new questions based on the most similar questions retrieved from the training data.