Few-shot Multi-hop Question Answering over Knowledge Base

TL;DR

This paper introduces an efficient pipeline for few-shot multi-hop KBQA using a pre-trained language model and beam search, enabling effective reasoning over knowledge bases with limited training data.

Contribution

The paper presents a novel pipeline with a data generation strategy and beam search to handle multi-hop reasoning in KBQA with few training samples.

Findings

Achieved 62.55% F1-score on CCKS2019 dataset.

Model maintains 58.54% F1-score with only 10% training data.

Demonstrated effective few-shot learning capability in KBQA.

Abstract

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.