HopPG: Self-Iterative Program Generation for Multi-Hop Question Answering over Heterogeneous Knowledge

TL;DR

HopPG introduces a self-iterative program generation framework that improves multi-hop question answering over heterogeneous knowledge bases by utilizing intermediate results for better fact retrieval and program generation.

Contribution

This paper proposes HopPG, a novel self-iterative approach that enhances multi-hop semantic parsing by leveraging previous execution results, addressing limitations of traditional methods.

Findings

Outperforms existing semantic parsing baselines on MMQA-T^2.

Significantly improves multi-hop question answering accuracy.

Effective in handling heterogeneous supporting facts.

Abstract

The semantic parsing-based method is an important research branch for knowledge-based question answering. It usually generates executable programs lean upon the question and then conduct them to reason answers over a knowledge base. Benefit from this inherent mechanism, it has advantages in the performance and the interpretability. However, traditional semantic parsing methods usually generate a complete program before executing it, which struggles with multi-hop question answering over heterogeneous knowledge. On one hand, generating a complete multi-hop program relies on multiple heterogeneous supporting facts, and it is difficult for generators to understand these facts simultaneously. On the other hand, this way ignores the semantic information of the intermediate answers at each hop, which is beneficial for subsequent generation. To alleviate these challenges, we propose a self-iterative framework for multi-hop program generation (HopPG) over heterogeneous knowledge, which leverages the previous execution results to retrieve supporting facts and generate subsequent programs hop by hop. We evaluate our model on MMQA-T^2, and the experimental results show that HopPG outperforms existing semantic-parsing-based baselines, especially on the multi-hop questions.