论文标题
部分可观测时空混沌系统的无模型预测
AutoQGS: Auto-Prompt for Low-Resource Knowledge-based Question Generation from SPARQL
论文作者
论文摘要
这项研究调查了基于知识的问题产生的任务（KBQG）。传统的KBQG的作品从知识图中的事实三元组中产生了问题，该问题无法表达复杂的操作，例如SPARQL中的聚合和比较。此外，由于大规模SPARQL问题对的昂贵注释，因此需要急切地探索来自SPARQL的KBQG。最近，由于经过自然语言（NL）-TO-NL范式训练的生成预训练的语言模型（PLM）已被证明对低资源生成有效，例如T5和Bart，因此如何有效利用它们来生成非NL Sparql的NL Question。为了应对这些挑战，提出了AutoQGS是SPARQL的低资源KBQG的自动提取方法。首先，我们提出要直接从SPARQL生成问题，以处理KBQG任务以处理复杂的操作。其次，我们提出了一个在大规模无监督的数据上训练的自动促销，将SPARQL重新描述为NL描述，从而平滑了从非NL SPARQL到NL问题的低资源转换。 WebQuestionsSP，ComlexWebQuestions 1.1和路径问题的实验结果表明，我们的模型可实现最新的性能，尤其是在低资源设置中。此外，为进一步的KBQG研究生成了330k Factoid复杂问题-sparql对的语料库。
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.
