Less is More: Data-Efficient Complex Question Answering over Knowledge Bases

TL;DR

This paper introduces NS-CQA, a data-efficient neural-symbolic framework for complex question answering over knowledge bases, achieving high performance with minimal training data by combining reinforcement learning, symbolic actions, and curriculum-guided rewards.

Contribution

The paper presents a novel reinforcement learning approach with symbolic actions, memory buffer, and adaptive rewards to improve data efficiency in complex KB question answering.

Findings

Outperforms state-of-the-art on CQA and WebQuestionsSP datasets.

Achieves high accuracy using only about 1% of training data on CQA.

Effective in handling higher complexity questions.

Abstract

Question answering is an effective method for obtaining information from knowledge bases (KB). In this paper, we propose the Neural-Symbolic Complex Question Answering (NS-CQA) model, a data-efficient reinforcement learning framework for complex question answering by using only a modest number of training samples. Our framework consists of a neural generator and a symbolic executor that, respectively, transforms a natural-language question into a sequence of primitive actions, and executes them over the knowledge base to compute the answer. We carefully formulate a set of primitive symbolic actions that allows us to not only simplify our neural network design but also accelerate model convergence. To reduce search space, we employ the copy and masking mechanisms in our encoder-decoder architecture to drastically reduce the decoder output vocabulary and improve model generalizability. We equip our model with a memory buffer that stores high-reward promising programs. Besides, we propose an adaptive reward function. By comparing the generated trial with the trials stored in the memory buffer, we derive the curriculum-guided reward bonus, i.e., the proximity and the novelty. To mitigate the sparse reward problem, we combine the adaptive reward and the reward bonus, reshaping the sparse reward into dense feedback. Also, we encourage the model to generate new trials to avoid imitating the spurious trials while making the model remember the past high-reward trials to improve data efficiency. Our NS-CQA model is evaluated on two datasets: CQA, a recent large-scale complex question answering dataset, and WebQuestionsSP, a multi-hop question answering dataset. On both datasets, our model outperforms the state-of-the-art models. Notably, on CQA, NS-CQA performs well on questions with higher complexity, while only using approximately 1% of the total training samples.