Pith. sign in

REVIEW 4 cited by

RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2205.06983 v2 pith:JLQVWALY submitted 2022-05-14 cs.CL cs.AIcs.DBcs.LG

Jiexing Qi , Jingyao Tang , Ziwei He , Xiangpeng Wan , Yu Cheng , Chenghu Zhou , Xinbing Wang , Quanshi Zhang
show 1 more author
Zhouhan Lin
This is my paper · ORCID
classification cs.CLcs.AIcs.DBcs.LG
keywords modelpretrainedrasatrelationalrelationsstructurestext-to-sqlintroducing
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Relational structures such as schema linking and schema encoding have been validated as a key component to qualitatively translating natural language into SQL queries. However, introducing these structural relations comes with prices: they often result in a specialized model structure, which largely prohibits using large pretrained models in text-to-SQL. To address this problem, we propose RASAT: a Transformer seq2seq architecture augmented with relation-aware self-attention that could leverage a variety of relational structures while inheriting the pretrained parameters from the T5 model effectively. Our model can incorporate almost all types of existing relations in the literature, and in addition, we propose introducing co-reference relations for the multi-turn scenario. Experimental results on three widely used text-to-SQL datasets, covering both single-turn and multi-turn scenarios, have shown that RASAT could achieve state-of-the-art results across all three benchmarks (75.5% EX on Spider, 52.6% IEX on SParC, and 37.4% IEX on CoSQL).

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Can the Rookies Cut the Tough Cookie? Exploring the Use of LLMs for SQL Equivalence Checking

    cs.DB 2024-12 conditional novelty 6.0 of 10

    LLMs, especially GPT-4, can classify SQL query equivalence on complex real-world assignment queries far beyond formal tools' coverage, but they systematically over-predict equivalence.

  2. Towards Automatic Evaluation of Task-Oriented Dialogue Flows

    cs.CL 2024-11 conditional novelty 6.0 of 10

    FuDGE and FF1 automatically score dialogue flow graphs by how compactly and completely they represent a corpus of task-oriented conversations.

  3. StreamLink: Large-Language-Model Driven Distributed Data Engineering System

    cs.DB 2025-05 conditional novelty 4.0 of 10

    A locally deployed LLM-based distributed data system converts natural language to SQL, and its fine-tuned Llama-3.1-8B model reaches 86.9% exact match and 89.7% execution accuracy on the Spider dev set.

  4. A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges

    cs.AI 2024-12 conditional

    A high-level review of benchmarks, models, applications, and challenges in LLM-based text-to-SQL, with no new experiments or methods.

Pith tools