COLING 2024main2 citations

TP-Link: Fine-grained Pre-Training for Text-to-SQL Parsing with Linking Information

Ziqiang Liu, Shujie Li, Zefeng Cai, Xiangyu Li, Yunshui Li, Chengming Li, Xiping Hu, Ruifeng Xu

Abstract

In this paper, we introduce an innovative pre-training framework TP-Link, which aims to improve context-dependent Text-to-SQL Parsing by leveraging Linking information. This enhancement is achieved through better representation of both natural language utterances and the database schema, ultimately facilitating more effective text-to-SQL conversations. We present two novel pre-training objectives: (i) utterance linking prediction (ULP) task that models intricate syntactic relationships among natural language utterances in context-dependent text-to-SQL scenarios, and (ii) schema linking prediction (SLP) task that focuses on capturing fine-grained schema linking relationships between the utterances and the database schema. Extensive experiments demonstrate that our proposed TP-Link achieves state-of-the-art performance on two leading downstream benchmarks (i.e., SParC and CoSQL).

BibTeX
@inproceedings{liu-etal-2024-tp,
    title = "{TP}-Link: Fine-grained Pre-Training for Text-to-{SQL} Parsing with Linking Information",
    author = "Liu, Ziqiang  and
      Li, Shujie  and
      Cai, Zefeng  and
      Li, Xiangyu  and
      Li, Yunshui  and
      Li, Chengming  and
      Hu, Xiping  and
      Xu, Ruifeng  and
      Yang, Min",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lrec-main.1451/",
    pages = "16686--16697"
}
TP-Link: Fine-grained Pre-Training for Text-to-SQL Parsing with Linking Information · COLING 2024