通过排序敏感预训练提升自然语言转SPARQL的准确性
Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training
- 引入三元组顺序纠正新目标，增强模型对SPARQL语法的敏感度
- 在三个主流数据集上达到当前最佳性能，减少三元组颠倒错误
- 适合需要精准知识图谱查询生成的研究者和开发者
将自然语言查询转化为SPARQL语句的语义解析对知识图谱问答系统至关重要。尽管像T5这样的预训练语言模型在文本到SPARQL任务中取得了显著进展，其生成结果仍存在明显的SPARQL语言特异性错误，如三元组颠倒。为解决这一问题并进一步提升性能，我们提出一种新的预训练阶段，采用三元组顺序纠正（TOC）目标，与常用的掩码语言建模（MLM）共同作用，以增强模型对三元组顺序和SPARQL语法的敏感性。该方法在三个广泛使用的基准测试上均达到了当前最优表现。
原文摘要 · Abstract (English)
Semantic parsing that translates natural language queries to SPARQL is of great importance for Knowledge Graph Question Answering (KGQA) systems. Although pre-trained language models like T5 have achieved significant success in the Text-to-SPARQL task, their generated outputs still exhibit notable errors specific to the SPARQL language, such as triplet flips. To address this challenge and further improve the performance, we propose an additional pre-training stage with a new objective, Triplet Order Correction (TOC), along with the commonly used Masked Language Modeling (MLM), to collectively enhance the model's sensitivity to triplet order and SPARQL syntax. Our method achieves state-of-the-art performances on three widely-used benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。