Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions

By Rui Zhang, Tao Yu, Heyang Er, Sungrok Shim, Eric Xue, Xi Victoria Lin, Tianze Shi, Caiming Xiong, Richard Socher, Dragomir R. Radev. 2019

161 citations recorded by the source corpus.

We focus on the cross-domain context-dependent text-to-SQL generation task. Based on the observation that adjacent natural language questions are often linguistically dependent and their corresponding SQL queries tend to overlap, we utilize the interaction history by editing the previous predicted query to improve the generation quality. Our editing mechanism views SQL as sequences and reuses generation results at the token level in a simple manner. It is flexible to change individual tokens and robust to error propagation. Furthermore, to deal with complex table structures in different domains, we employ an utterance-table encoder and a table-aware decoder to incorporate the context of the user utterance and the table schema. We evaluate our approach on the SParC dataset and demonstrate the benefit of editing compared with the state-of-the-art baselines which generate SQL from scratch. Our code is available at https://github.com/ryanzhumich/sparc_atis_pytorch.

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

A Survey of Data Augmentation Approaches for NLP (2021, methodology): “Zhang et al. (2019b) explore multi-task transfer, or the use of annotated data from other tasks.”
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers (2019, methodology): “We found that when augmented with BERT, RAT-SQL becomes more consistent in terms of both metrics, indicating the pre-trained representations of BERT are beneﬁcial for handling paraphrases.”
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing (2020, background): “More and more work (Zhang et al., 2019b; Herzig et al., 2020b; Campagna et al., 2020; Zhong et al., 2020) shows utilizing augmented data doesn’t always result in a signiﬁcant performance gain in cross-domain semantic parsing end tasks.”
Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback (2020, background): “We adapt EditSQL for the correction task by providing the question and the feedback as the utterances at turn one and two respectively, and we force it to use the mispredicted parse the the prediction of turn one (rather than predicting it).”
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).”
Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing (2021, methodology): “Beyond that, Zhang et al. (2019) present an edit-based method that reuses the SQL query generated in the previous time step through editing, which achieves promising results.”
Task-Oriented Dialogue as Dataflow Synthesis (2020, background): “, 2018) or tokens (Zhang et al., 2019) from previously-generated queries.”
Context Dependent Semantic Parsing: A Survey (2020, methodology): “Compared with CISP, which usually assumes that the information within the utterance is complete, CDSP is expected to tackle challenges posed by involving context in the parsing process (Liang, 2016; Suhr et al., 2018; Zhang et al., 2019; Liu et al., 2020).”
Few-Shot Semantic Parsing for New Predicates (2021, methodology): “…is to exploit available 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…”
Photon: A Robust Cross-Domain Text-to-SQL System (2020, methodology): “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.”
NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction (2021, methodology): “NL-EDIT significantly increases the correction accuracy over the top baseline (EditSQL+Feedback) by more than 16% and it also outperforms oracle re-ranking by around 5%.”
CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (2019, background): “Recent works (Suhr et al., 2018; Zhang et al., 2019) have built context-dependent text-to-SQL systems on top of these datasets.”
Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases (2020, methodology): “odel that maps an input question � = �1,...,� |� to its corresponding logical form � = 𝑦1,...,𝑦 � . The entire model is based on Seq2Seq [2, 38], which is commonly used in many semantic parsing tasks [12, 15, 19, 20, 48]. Seq2Seq comprises an encoder that encodes input� into vectors and a decoder ”
TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data (2020, methodology): “Global–GNN (Bogin et al., 2019a) 52.7 EditSQL + B ERT (Zhang et al., 2019a) 57.6 RatSQL (Wang et al., 2019a) 60.9 IRNet + B ERT (Guo et al., 2019) 60.3 + Memory + Coarse-to-Fine 61.9 IRNet V2 + B ERT 63.9 RyanSQL + B ERT (Choi et al., 2020) 66.6 Our System based on TranX (Yin and Neubig, 2018…”