X-SQL: reinforce schema representation with context

By Pengcheng He, Yi Mao, Kaushik Chakrabarti, Weizhu Chen. 2019

103 citations recorded by the source corpus.

In this work, we present X-SQL, a new network architecture for the problem of parsing natural language to SQL query. X-SQL proposes to enhance the structural schema representation with the contextual output from BERT-style pre-training model, and together with type information to learn a new schema representation for down-stream tasks. We evaluated X-SQL on the WikiSQL dataset and show its new state-of-the-art performance.

Subfields: Artificial Intelligence, Large Language Models, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jianfeng Gao
2. Graham Neubig
3. Luke S. Zettlemoyer
4. Weizhu Chen
5. Wen-tau Yih
6. Mohit Bansal
7. Sebastian Riedel
8. Percy Liang

In Large Language Models

1. Weizhu Chen
2. Pengcheng He
3. Jianfeng Gao
4. Xiaodong Liu
5. Daniel Klein
6. Wen-tau Yih
7. Graham Neubig
8. Sebastian Riedel

In Natural Language Processing

1. Jianfeng Gao
2. Graham Neubig
3. Wen-tau Yih
4. Weizhu Chen
5. Xiaodong Liu
6. Luke S. Zettlemoyer
7. Sebastian Riedel
8. Mohit Bansal

Citations in the corpus

• DeBERTa: Decoding-enhanced BERT with Disentangled Attention (2020, methodology): “These PLMs have been fine-tuned using task-specific labels and created new state-of-the-art in many downstream natural language processing (NLP) tasks [13, 14, 15, 16, 17, 18].”
• A Discrete Hard EM Approach for Weakly Supervised Question Answering (2019, neutral): “…et al., 2019) 74.9 74.8 MML 70.6 70.5 Ours 84.4 83.9 Fully-supervised setting SQLNet (Xu et al., 2018) 69.8 68.0 TypeSQL (Yu et al., 2018b) 74.5 73.5 Coarse2Fine (Dong and Lapata, 2018) 79.0 78.5 SQLova (Hwang et al., 2019) 87.2 86.2 X-SQL (He et al., 2019) 89.5 88.7 Table 4: Results on W IKI SQL.”
• TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data (2020, background): “…al., 2016; Neelakantan et al., 2016 2018)), and BERT-family models for learning joint contextual representations of utterances and tables, but with domain-specific approaches to encode the structured information in tables (Hwang et al., 2019; He et al., 2019; Guo et al., 2019; Zhang et al., 2019a).”
• Semantic Evaluation for Text-to-SQL with Distilled Test Suite (2020, methodology): “Specifically, we consider the model-predicted queries from the following eight models: MQAN unordered (McCann et al., 2018), X-SQL (He et al., 2019), HydraNet with / without Execution Guidance (Lyu et al., 2020), IncSQL (Shi et al., 2018), SQLova with / without Execution Guidance (Hwang et al.,…”