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

Yuncheng Hua, Yuan-Fang Li, Gholamreza Haffari, Guilin Qi, Tongtong Wu

Question Answering Long Paper

Zoom-10D: Nov 18, Zoom-10D: Nov 18 (01:00-02:00 UTC) [Join Zoom Meeting]

You can open the pre-recorded video in a separate window.

Abstract: 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 meta-training on tasks constructed from only 1% of the training set. We have released our code at https://github.com/DevinJake/MRL-CQA.
NOTE: Video may display a random order of authors. Correct author list is at the top of this page.

Connected Papers in EMNLP2020

Similar Papers

Zero-Shot Cross-Lingual Transfer with Meta Learning
Farhad Nooralahzadeh, Giannis Bekoulis, Johannes Bjerva, Isabelle Augenstein,
Unsupervised Question Decomposition for Question Answering
Ethan Perez, Patrick Lewis, Wen-tau Yih, Kyunghyun Cho, Douwe Kiela,
Efficient Meta Lifelong-Learning with Limited Memory
Zirui Wang, Sanket Vaibhav Mehta, Barnabas Poczos, Jaime Carbonell,
Training Question Answering Models From Synthetic Data
Raul Puri, Ryan Spring, Mohammad Shoeybi, Mostofa Patwary, Bryan Catanzaro,