Program Transfer for Answering Complex Questions over Knowledge Bases

TL;DR

This paper introduces a program transfer approach with a two-stage parsing framework and ontology-guided pruning to improve question answering over knowledge bases, especially when program annotations are scarce.

Contribution

It proposes a novel two-stage parsing framework with ontology-guided pruning for program transfer, enhancing complex question answering on low-resource knowledge bases.

Findings

Outperforms state-of-the-art methods on ComplexWebQuestions and WebQuestionSP.

Demonstrates the effectiveness of program transfer in low-resource KB settings.

Shows significant accuracy improvements over existing approaches.

Abstract

Program induction for answering complex questions over knowledge bases (KBs) aims to decompose a question into a multi-step program, whose execution against the KB produces the final answer. Learning to induce programs relies on a large number of parallel question-program pairs for the given KB. However, for most KBs, the gold program annotations are usually lacking, making learning difficult. In this paper, we propose the approach of program transfer, which aims to leverage the valuable program annotations on the rich-resourced KBs as external supervision signals to aid program induction for the low-resourced KBs that lack program annotations. For program transfer, we design a novel two-stage parsing framework with an efficient ontology-guided pruning strategy. First, a sketch parser translates the question into a high-level program sketch, which is the composition of functions. Second, given the question and sketch, an argument parser searches the detailed arguments from the KB for functions. During the searching, we incorporate the KB ontology to prune the search space. The experiments on ComplexWebQuestions and WebQuestionSP show that our method outperforms SOTA methods significantly, demonstrating the effectiveness of program transfer and our framework. Our codes and datasets can be obtained from https://github.com/THU-KEG/ProgramTransfer.