Few-shot Multi-hop Question Answering over Knowledge Base
This addresses the challenge of limited training data and exponential search space in knowledge base question answering, with incremental improvements in few-shot learning for domain-specific applications.
The paper tackles the problem of few-shot multi-hop question answering over knowledge bases by proposing an efficient pipeline method with a pre-trained language model and data generation strategy, achieving an F1-score of 62.55% on a test dataset and 58.54% with only 10% of training data.
KBQA is a task that requires to answer questions by using semantic structured information in knowledge base. Previous work in this area has been restricted due to the lack of large semantic parsing dataset and the exponential growth of searching space with the increasing hops of relation paths. In this paper, we propose an efficient pipeline method equipped with a pre-trained language model. By adopting Beam Search algorithm, the searching space will not be restricted in subgraph of 3 hops. Besides, we propose a data generation strategy, which enables our model to generalize well from few training samples. We evaluate our model on an open-domain complex Chinese Question Answering task CCKS2019 and achieve F1-score of 62.55% on the test dataset. In addition, in order to test the few-shot learning capability of our model, we ramdomly select 10% of the primary data to train our model, the result shows that our model can still achieves F1-score of 58.54%, which verifies the capability of our model to process KBQA task and the advantage in few-shot Learning.