针对领域特定值识别难题，提出数据平衡与过采样方法提升SQL生成准确率。
Domain Specific Question to SQL Conversion with Embedded Data Balancing Technique
- 引入数据平衡与过采样技术，增强模型对领域值的识别能力。
- 在WikiSQL上相比顶尖模型提升10.98%准确率，显著改善失败案例。
- 适合需要高精度领域SQL转换的场景，如医疗、金融等垂直领域。
深度学习在自然语言处理中的发展催生了由编码器-解码器构成的文本转结构化查询语言模型。尽管研究者尝试了模式链接、表类型感知、值提取等中间处理方式以生成准确的SQL查询，但错误分析显示，29%的错误源于系统无法理解用户问题中表达的具体数值。这一挑战在涉及领域术语和特定值条件时尤为突出，传统方法难以保持一致性和精确性。为此，本文提出两种改进：实施数据平衡技术并过采样领域特定查询，以优化模型架构，提升值识别能力，并针对领域问题进行微调。该方案在WikiSQL数据集上的实验表明，相比现有最优模型，准确率提升了10.98%，显著优于传统方法。
原文摘要 · Abstract (English)
The rise of deep learning in natural language processing has fostered the creation of text to structured query language models composed of an encoder and a decoder. Researchers have experimented with various intermediate processing like schema linking, table type aware, value extract. To generate accurate SQL results for the user question. However error analysis performed on the failed cases on these systems shows, 29 percentage of the errors would be because the system was unable to understand the values expressed by the user in their question. This challenge affects the generation of accurate SQL queries, especially when dealing with domain-specific terms and specific value conditions, where traditional methods struggle to maintain consistency and precision. To overcome these obstacles, proposed two intermediations like implementing data balancing technique and over sampling domain-specific queries which would refine the model architecture to enhance value recognition and fine tuning the model for domain-specific questions. This proposed solution achieved 10.98 percentage improvement in accuracy of the model performance compared to the state of the art model tested on WikiSQL dataset. to convert the user question accurately to SQL queries. Applying oversampling technique on the domain-specific questions shown a significant improvement as compared with traditional approaches.
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。