Less is more: Data-efficient complex question answering over knowledge bases

Yuncheng Hua, Yuan-Fang Li, Guilin Qi, Wei Wu, Jingyao Zhang, Daiqing Qi

Abstract: Highlights • We propose a neural-symbolic approach for complex question answering and augment it with a memory buffer to maintain the previous successful trials for each training question. • We utilize the memory to guide the model to replay and re-sample the promising trials more frequently, thus mitigating the data-inefficiency problem • We employ a curriculum-learning scheme that adaptively combines novelty and proximity to balance the exploration-exploitation trade-off for the model. • We propose several simple yet effective techniques to reduce search space, improve model generalizability, and accelerate convergence. • We conduct experiments on two complex question answering datasets to verify the effectiveness of the provided approach. 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.