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

arXiv: https://arxiv.org/abs/2010.15877 · HTML: https://mlsanity.com/paper/2010.15877/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2020.

## Built on by (most cited first, 16 of 16)

- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [Few-shot In-context Learning for Knowledge Base Question Answering](https://mlsanity.com/paper/2305.01750/) (2023)
- [Complex Knowledge Base Question Answering: A Survey](https://mlsanity.com/paper/2108.06688/) (2021)
- [Meta Learning for Natural Language Processing: A Survey](https://mlsanity.com/paper/2205.01500/) (2022)
- [Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection](https://mlsanity.com/paper/2105.09509/) (2021)
- [Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs](https://mlsanity.com/paper/2105.11225/) (2021)
- [Embedding Hallucination for Few-Shot Language Fine-tuning](https://mlsanity.com/paper/2205.01307/) (2022)
- [Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text](https://mlsanity.com/paper/2109.02289/) (2021)
- [Can Open Domain Question Answering Systems Answer Visual Knowledge Questions?](https://mlsanity.com/paper/2202.04306/) (2022)
- [Aligning Multiple Knowledge Graphs in a Single Pass](https://mlsanity.com/paper/2408.00662/) (2024)
- [Reinforced Approximate Exploratory Data Analysis](https://mlsanity.com/paper/2212.06225/) (2022)
- [Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment](https://mlsanity.com/paper/2212.13036/) (2022)
- [A Review of Reinforcement Learning for Natural Language Processing, and Applications in Healthcare](https://mlsanity.com/paper/2310.18354/) (2023)
- [Few-shot Multi-hop Question Answering over Knowledge Base](https://mlsanity.com/paper/2112.11909/) (2021)
- [TransPrompt v2: A Transferable Prompting Framework for Cross-task Text Classification](https://mlsanity.com/paper/2308.15010/) (2023)
- [From text to multimodal: a survey of adversarial example generation in question answering systems](https://mlsanity.com/paper/2312.16156/) (2023)

## Abstract (arXiv)

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. The meta-learned policy is then used to learn a good programming policy, utilizing the trial trajectories and their rewards for similar questions in the support set. Our method achieves state-of-the-art performance on the CQA dataset (Saha et al., 2018) while using only five trial trajectories for the top-5 retrieved questions in each support set, and metatraining on tasks constructed from only 1% of the training set. We have released our code at https://github.com/DevinJake/MRL-CQA.