Hybrid Ranking Network for Text-to-SQL

• URL: http://arxiv.org/abs/2008.04759v1
• Date: Tue, 11 Aug 2020 15:01:52 GMT
• Title: Hybrid Ranking Network for Text-to-SQL
• Authors: Qin Lyu, Kaushik Chakrabarti, Shobhit Hathi, Souvik Kundu, Jianwen Zhang, Zheng Chen
• Abstract summary: We propose a neat approach called Hybrid Ranking Network (HydraNet) which breaks down the problem into column-wise ranking and decoding. Experiments on the dataset show that the proposed approach is very effective, achieving the top place on the leaderboard.
• Score: 9.731436359069493
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we study how to leverage pre-trained language models in Text-to-SQL. We argue that previous approaches under utilize the base language models by concatenating all columns together with the NL question and feeding them into the base language model in the encoding stage. We propose a neat approach called Hybrid Ranking Network (HydraNet) which breaks down the problem into column-wise ranking and decoding and finally assembles the column-wise outputs into a SQL query by straightforward rules. In this approach, the encoder is given a NL question and one individual column, which perfectly aligns with the original tasks BERT/RoBERTa is trained on, and hence we avoid any ad-hoc pooling or additional encoding layers which are necessary in prior approaches. Experiments on the WikiSQL dataset show that the proposed approach is very effective, achieving the top place on the leaderboard.

Related papers

• SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended) [53.95151604061761]
  This paper introduces the framework for enhancing Text-to- filtering using large language models (LLMs) With few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error analyses. With instruction fine-tuning, we delve deep in understanding the critical paradigms that influence the performance of tuned LLMs.
  arXiv  Detail & Related papers  (2023-05-26T21:39:05Z)
• STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing [64.80483736666123]
  We propose a novel pre-training framework STAR for context-dependent text-to- parsing. In addition, we construct a large-scale context-dependent text-to-the-art conversation corpus to pre-train STAR. Extensive experiments show that STAR achieves new state-of-the-art performance on two downstream benchmarks.
  arXiv  Detail & Related papers  (2022-10-21T11:30:07Z)
• A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions [102.8606542189429]
  The goal of text-to-corpora parsing is to convert a natural language (NL) question to its corresponding structured query language () based on the evidences provided by databases. Deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output query.
  arXiv  Detail & Related papers  (2022-08-29T14:24:13Z)
• S$^2$SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers [66.78665327694625]
  We propose S$2$, injecting Syntax to question- encoder graph for Text-to- relational parsing. We also employ the decoupling constraint to induce diverse edge embedding, which further improves the network's performance. Experiments on the Spider and robustness setting Spider-Syn demonstrate that the proposed approach outperforms all existing methods when pre-training models are used.
  arXiv  Detail & Related papers  (2022-03-14T09:49:15Z)
• Weakly Supervised Text-to-SQL Parsing through Question Decomposition [53.22128541030441]
  We take advantage of the recently proposed question meaning representation called QDMR. Given questions, their QDMR structures (annotated by non-experts or automatically predicted) and the answers, we are able to automatically synthesizesql queries. Our results show that the weakly supervised models perform competitively with those trained on NL- benchmark data.
  arXiv  Detail & Related papers  (2021-12-12T20:02:42Z)
• Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning [25.69875174742935]
  Single-table text-to-one aims to transform a natural language question into a query according to one single table. We propose a new approach for the zero-shot text-to-one task which does not rely on any additional manual annotations. We conduct extensive experiments on a public open-domain text-to-one dataset and a domain-specific dataset E.
  arXiv  Detail & Related papers  (2021-09-12T01:01:28Z)
• Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing [40.65143087243074]
  This paper presents a simple yet effective data augmentation framework. First, given a database, we automatically produce a large amount ofsql queries based on an abstract syntax tree grammar citeyintranx. Second, we propose a hierarchicalsql-to-question generation model to obtain high-quality natural language questions.
  arXiv  Detail & Related papers  (2021-03-03T07:37:38Z)
• GP: Context-free Grammar Pre-training for Text-to-SQL Parsers [7.652782364282768]
  Grammar Pre-training (GP) is proposed to decode deep relations between question and database. Experiments show that our method is easier to converge during training and has excellent robustness.
  arXiv  Detail & Related papers  (2021-01-25T05:41:31Z)
• Structure-Grounded Pretraining for Text-to-SQL [75.19554243393814]
  We present a novel weakly supervised StructureStrued pretraining framework (G) for text-to-LARGE. We identify a set of novel prediction tasks: column grounding, value grounding and column-value mapping, and leverage them to pretrain a text-table encoder.
  arXiv  Detail & Related papers  (2020-10-24T04:35:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.