Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation

By Jiaqi Guo, Zecheng Zhan, Yan Gao, Yan Xiao, Jian-Guang Lou, Ting Liu, Dongmei Zhang. 2019

493 citations recorded by the source corpus.

We present a neural approach called IRNet for complex and cross-domain Text-to-SQL. IRNet aims to address two challenges: 1) the mismatch between intents expressed in natural language (NL) and the implementation details in SQL; 2) the challenge in predicting columns caused by the large number of out-of-domain words. Instead of end-to-end synthesizing a SQL query, IRNet decomposes the synthesis process into three phases. In the first phase, IRNet performs a schema linking over a question and a database schema. Then, IRNet adopts a grammar-based neural model to synthesize a SemQL query which is an intermediate representation that we design to bridge NL and SQL. Finally, IRNet deterministically infers a SQL query from the synthesized SemQL query with domain knowledge. On the challenging Text-to-SQL benchmark Spider, IRNet achieves 46.7% accuracy, obtaining 19.5% absolute improvement over previous state-of-the-art approaches. At the time of writing, IRNet achieves the first position on the Spider leaderboard.

Subfields: Artificial Intelligence, Information Systems, 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

In Information Systems

In Natural Language Processing

Citations in the corpus

Break It Down: A Question Understanding Benchmark (2020, background): “Question Decomposition Recent work on QA through question decomposition has focused mostly on single modalities (Gupta and Lewis, 2018; Guo et al., 2019; Min et al., 2019b).”
Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers (2021, background): “, 2019) or sequences of parse actions (Chen et al., 2018; Cheng et al., 2019; Lin et al., 2019; Zhang et al., 2019; Yin and Neubig, 2018; Chen et al., 2018; Guo et al., 2019; Wang et al., 2020a; Li et al., 2021).”
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers (2019, methodology): “…RAT-SQL (ours) 62.7 57.2 With BERT: EditSQL + BERT (Zhang et al., 2019) 57.6 53.4 GNN + Bertrand-DR (Kelkar et al., 2020) 57.9 54.6 IRNet V2 + BERT (Guo et al., 2019) 63.9 55.0 RYANSQL V2 + BERT (Choi et al., 2020) We used the Adam optimizer (Kingma and Ba, 2015) with the default hyperparameters.”
Grounded Adaptation for Zero-shot Executable Semantic Parsing (2020, methodology): “For language-to-SQL zero-shot semantic parsing, a variety of methods have been proposed to generalize to new databases by selecting from table schemas in the new database (Zhang et al., 2019; Guo et al., 2019).”
Photon: A Robust Cross-Domain Text-to-SQL System (2020, background): “We utilize the BERT-based contex-tualized question-schema representations produced by the encoder in Figure 5 to extract the confusion span in a question hence predict its translatability.”
Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions (2020, methodology): “separate the general formula of action sequences with specific instances of objects in action sequences, which has been shown to help in Text-to-SQL translation (Guo et al., 2019).”
Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions (2021, background): “…community, mapping natural language utterances to SQL queries for databases, also known as SQLbased semantic parsing, has attracted increasing attention (Yin and Neubig, 2017; Dong and Lapata, 2018b; Guo et al., 2019; Wang et al., 2020; Bogin et al., 2019; Lin et al., 2020; Yin and Neubig, 2019).”
SmBoP: Semi-autoregressive Bottom-up Semantic Parsing (2020, background): “Relational algebra Guo et al. (2019) have shown recently that the mismatch between natu-ral language and SQL leads to parsing difﬁculties.”
Few-Shot Semantic Parsing for New Predicates (2021, methodology): “…resources, such as knowledge bases (Krishnamurthy et al., 2017; Herzig and Berant, 2018; Chang et al., 2019; Lee, 2019; Zhang et al., 2019a; Guo et al., 2019; Wang et al., 2019), semantic features in different domains (Dadashkarimi et al., 2018; Li et al., 2020), or unlabeled data (Yin et…”
PlotCoder: Hierarchical Decoding for Synthesizing Visualization Code in Programmatic Context (2021, unknown): “…schema linking techniques proposed for semantic parsing with structured inputs, such as text to SQL tasks (Iyer et al., 2017; Wang et al., 2019a; Guo et al., 2019), P LOT C ODER ’s encoder connects the embedding of the natural language descriptions with their corresponding code fragments in…”
CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (2019, unknown): “(Warren and Pereira, 1982; Zettlemoyer and Collins, 2005; Popescu et al., 2003; Li et al., 2006; Li and Jagadish, 2014; Iyer et al., 2017; Zhong et al., 2017; Xu et al., 2017; Yu et al., 2018a; Dong and Lapata, 2018; FineganDollak et al., 2018; Guo et al., 2019; Bogin et al., 2019).”
Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions (2019, background): “…(Yu et al., 2018b) 18.9 19.7 +data augmentation (Yu et al., 2018b) 24.8 27.2 Lee (2019) 28.5 24.3 GNN (Bogin et al., 2019) 40.7 39.4 IRNet (Guo et al., 2019) 53.2 46.7 IRNet (BERT) (Guo et al., 2019) 61.9 2019) who achieve state-of-the-art performance by using an intermediate…”
RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL (2023, background): “Because there is a huge gap between natural language questions and their corresponding SQL queries, some works have focused on how to design an efficient intermediate representation (IR) to bridge the aforementioned gap (Yu et al. 2018b; Guo et al. 2019; Gan et al. 2021b).”
Is a Question Decomposition Unit All We Need? (2022, methodology): “Decomposition using text-to-SQL query conversion has also been studied (Guo et al., 2019).”
Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing (2021, methodology): “Guo et al. (2019) perform schema linking over a question and database schema using customized type vectors for alignment and adopts a grammar-based model (Yin and Neubig 2017) to synthesize an intermediate representation.”
NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction (2021, unknown): “Several recent text-to-SQL models have been introduced (Yu et al., 2018a; Zhang et al., 2019; Guo et al., 2019; Wang et al., 2020, inter alia) as a result of the availability of SPIDER (Yu et al., 2018b), a large dataset of schema, questions and gold parses spanning several databases in different…”
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs (2023, methodology): “For example, IRNET [12] designs an encoder consisting of attention-based Bi-LSTM for learning question and schema representations, and a decoder to predict SQLs based on the encoded intermediate representations.”
Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation (2023, methodology): “With rapid advancement of deep learning, numerous techniques are applied to help Text-to-SQL task, such as attention mechanism [23], graph representation [14, 20, 32, 42, 46, 50], syntax parsing [12, 19, 35, 43], etc.”