paper-with-me

홈 › Papers

SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation

2023-10-27 · Adrián Bazaga, Pietro Liò, Gos Micklem

In recent years, the task of text-to-SQL translation, which converts natural language questions into executable SQL queries, has gained significant attention for its potential to democratize data access. Despite its promise, challenges such as adapting to unseen databases and aligning natural language with SQL syntax have hindered widespread adoption. To overcome these issues, we introduce SQLformer, a novel Transformer architecture specifically crafted to perform text-to-SQL translation tasks. Our model predicts SQL queries as abstract syntax trees (ASTs) in an autoregressive way, incorporating structural inductive bias in the encoder and decoder layers. This bias, guided by database table and column selection, aids the decoder in generating SQL query ASTs represented as graphs in a Breadth-First Search canonical order. Our experiments demonstrate that SQLformer achieves state-of-the-art performance across six prominent text-to-SQL benchmarks.

📄 PDF Abstract BibTeX arXiv:2310.18376

Code (1)

adrianbzg/sqlformer 공식 구현 pytorch

Tasks

DecoderGraph GenerationInductive BiasText to SQLText-To-SQLTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Autoregressive Models for Knowledge Graph Generation

2026-02-06 · Thiviyan Thanapalasingam, Antonis Vozikis, Peter Bloem, Paul Groth arxiv

Knowledge Graph (KG) generation requires models to learn complex semantic dependencies between triples while maintaining domain validity constraints. Unlike link prediction, which scores triples independently, generative…

Computational EfficiencyGraph GenerationLink Prediction

Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graphs

2021-11-01 · Yongrui Chen, Huiying Li, Guilin Qi, Tianxing Wu 외

Query graph construction aims to construct the correct executable SPARQL on the KG to answer natural language questions. Although recent methods have achieved good results using neural network-based query graph ranking, …

graph constructionGraph GenerationGraph RankingKnowledge Base Question Answering+1

G3PT: Unleash the power of Autoregressive Modeling in 3D Generation via Cross-scale Querying Transformer

2024-09-10 · Jinzhi Zhang, Feng Xiong, Mu Xu

Autoregressive transformers have revolutionized generative models in language processing and shown substantial promise in image and video generation. However, these models face significant challenges when extended to 3D …

3D GenerationVideo Generation

Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation

2025-07-24 · Shiyuan Li, Yixin Liu, Qingsong Wen, Chengqi Zhang 외 arxiv

Multi-agent systems (MAS) based on large language models (LLMs) have emerged as a powerful solution for dealing with complex problems across diverse domains. The effectiveness of MAS is critically dependent on its collab…

Graph Generation

Towards Fast Graph Generation via Autoregressive Noisy Filtration Modeling

2025-02-04 · Markus Krimmel, Jenna Wiens, Karsten Borgwardt, Dexiong Chen

Graph generative models often face a critical trade-off between learning complex distributions and achieving fast generation speed. We introduce Autoregressive Noisy Filtration Modeling (ANFM), a novel approach that addr…

Graph GenerationTopological Data Analysis