每日文献雷达

2026-07-16

Research Radar / 自动检索 · 结构阅读 · 博客沉淀

今日入选

  • IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles(69 citations; appeared 4x before)
  • SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging(21 citations; appeared 4x before)
  • Data Readiness for Natural Language Processing(code signal; 2 citations; appeared 3x before)

1. IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles

        - **来源**:deepxiv
        - **分数**:0.106
        - **入选原因**:69 citations; appeared 4x before
        - **摘要**:We present a sequence-to-action parsing approach for the natural language to SQL task that incrementally fills the slots of a SQL query with feasible actions from a pre-defined inventory. To account for the fact that typically there are multiple correct SQL queries with the same ...
  • 链接https://arxiv.org/abs/1809.05054

          <div style="margin-top: 2rem; padding: 1rem; border-left: 3px solid #4a90d9; font-size: 0.9rem; opacity: 0.85;">
          完整深度阅读见博客文章,使用结构化三元组方法拆解论文逻辑。
          </div>
    

2. SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging

        - **来源**:deepxiv
        - **分数**:0.1035
        - **入选原因**:21 citations; appeared 4x before
        - **摘要**:Recent advances in Text-to-SQL have largely focused on the SQLite dialect, neglecting the diverse landscape of SQL dialects like BigQuery and PostgreSQL. This limitation is due to the diversity in SQL syntaxes and functions, along with the high cost of collecting and curating SQL...
  • 链接https://arxiv.org/abs/2408.12733

          <div style="margin-top: 2rem; padding: 1rem; border-left: 3px solid #4a90d9; font-size: 0.9rem; opacity: 0.85;">
          完整深度阅读见博客文章,使用结构化三元组方法拆解论文逻辑。
          </div>
    

3. Data Readiness for Natural Language Processing

        - **来源**:deepxiv
        - **分数**:0.0869
        - **入选原因**:code signal; 2 citations; appeared 3x before
        - **摘要**:This document concerns data readiness in the context of machine learning and Natural Language Processing. It describes how an organization may proceed to identify, make available, validate, and prepare data to facilitate automated analysis methods. The contents of the document is...
  • 链接https://arxiv.org/abs/2009.02043

          <div style="margin-top: 2rem; padding: 1rem; border-left: 3px solid #4a90d9; font-size: 0.9rem; opacity: 0.85;">
          完整深度阅读见博客文章,使用结构化三元组方法拆解论文逻辑。
          </div>