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

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


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.
Anthology ID:
2020.emnlp-main.469
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5827–5837
Language:
URL:
https://aclanthology.org/2020.emnlp-main.469
DOI:
10.18653/v1/2020.emnlp-main.469
Bibkey:
Cite (ACL):
Yuncheng Hua, Yuan-Fang Li, Gholamreza Haffari, Guilin Qi, and Tongtong Wu. 2020. Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5827–5837, Online. Association for Computational Linguistics.
Cite (Informal):
Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning (Hua et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.469.pdf
Video:
 https://slideslive.com/38939385
Code
 DevinJake/MRL-CQA