AutoQGS: Auto-Prompt for Low-Resource Knowledge-based Question Generation from SPARQL

TL;DR

AutoQGS introduces an auto-prompt method that enables low-resource knowledge-based question generation from SPARQL queries by directly generating questions and rephrasing SPARQL into natural language descriptions, achieving state-of-the-art results.

Contribution

The paper presents a novel auto-prompt approach that effectively generates questions from SPARQL in low-resource scenarios, handling complex operations and rephrasing SPARQL into natural language.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively handles complex SPARQL operations.

Generates a large corpus of question-SPARQL pairs for future research.

Abstract

This study investigates the task of knowledge-based question generation (KBQG). Conventional KBQG works generated questions from fact triples in the knowledge graph, which could not express complex operations like aggregation and comparison in SPARQL. Moreover, due to the costly annotation of large-scale SPARQL-question pairs, KBQG from SPARQL under low-resource scenarios urgently needs to be explored. Recently, since the generative pre-trained language models (PLMs) typically trained in natural language (NL)-to-NL paradigm have been proven effective for low-resource generation, e.g., T5 and BART, how to effectively utilize them to generate NL-question from non-NL SPARQL is challenging. To address these challenges, AutoQGS, an auto-prompt approach for low-resource KBQG from SPARQL, is proposed. Firstly, we put forward to generate questions directly from SPARQL for the KBQG task to handle complex operations. Secondly, we propose an auto-prompter trained on large-scale unsupervised data to rephrase SPARQL into NL description, smoothing the low-resource transformation from non-NL SPARQL to NL question with PLMs. Experimental results on the WebQuestionsSP, ComlexWebQuestions 1.1, and PathQuestions show that our model achieves state-of-the-art performance, especially in low-resource settings. Furthermore, a corpus of 330k factoid complex question-SPARQL pairs is generated for further KBQG research.