5,936 Hits in 3.4 sec

Improving Text-to-SQL with Schema Dependency Learning [article]

Binyuan Hui, Xiang Shi, Ruiying Geng, Binhua Li, Yongbin Li, Jian Sun, Xiaodan Zhu
2021 arXiv   pre-print
In this paper, we present the Schema Dependency guided multi-task Text-to-SQL model (SDSQL) to guide the network to effectively capture the interactions between questions and schemas.  ...  Text-to-SQL aims to map natural language questions to SQL queries.  ...  Schema Dependency Learning Data Construction In order to capture the explicit and complex interaction between questions and headers, we propose the schema dependency learning task.  ... 
arXiv:2103.04399v2 fatcat:ndilbekgszfvhi5ivj42yremby

CQR-SQL: Conversational Question Reformulation Enhanced Context-Dependent Text-to-SQL Parsers [article]

Dongling Xiao, Linzheng Chai, Qian-Wen Zhang, Zhao Yan, Zhoujun Li, Yunbo Cao
2022 arXiv   pre-print
Context-dependent text-to-SQL is the task of translating multi-turn questions into database-related SQL queries.  ...  In this paper, we propose CQR-SQL, which uses auxiliary Conversational Question Reformulation (CQR) learning to explicitly exploit schema and decouple contextual dependency for SQL parsing.  ...  Conclusions We propose CQR-SQL, a novel context-dependent text-to-SQL approach that explicitly comprehends the schema and conversational dependency through latent CQR learning.  ... 
arXiv:2205.07686v2 fatcat:nh2utaetdfes5noa4esf64ijyq

S^2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers [article]

Binyuan Hui, Ruiying Geng, Lihan Wang, Bowen Qin, Bowen Li, Jian Sun, Yongbin Li
2022 arXiv   pre-print
In this paper, we propose S^2SQL, injecting Syntax to question-Schema graph encoder for Text-to-SQL parsers, which effectively leverages the syntactic dependency information of questions in text-to-SQL  ...  to improve the performance.  ...  The de facto method for text-to-SQL employs an encoderdecoder architecture. In this paper we focus on improving the encoder part.  ... 
arXiv:2203.06958v1 fatcat:4q2dvvcngbfu5nqhgv4cfdiesu

A Review of Cross-Domain Text-to-SQL Models

Yujian Gan, Matthew Purver, John Woodward
2021 Zenodo  
an environment where it is more challenging to build schema linking and also worth studying combing the advantage of each model toward text-to-SQL.  ...  The leaderboards of WikiSQL and Spider show that many researchers propose their models trying to solve the text-to-SQL problem.  ...  Acknowledgements We would like to thank Denis Newman-Griffis for his meticulous guidance in revising the cameraready version and the anonymous reviewers for their helpful comments.  ... 
doi:10.5281/zenodo.4699228 fatcat:vy3y75odo5bitakwdpsbkkosdq

Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker [article]

Amol Kelkar, Rohan Relan, Vaishali Bhardwaj, Saurabh Vaichal, Chandra Khatri, Peter Relan
2020 arXiv   pre-print
We propose a novel discriminative re-ranker to improve the performance of generative text-to-SQL models by extracting the best SQL query from the beam output predicted by the text-to-SQL generator, resulting  ...  To simplify this task, text-to-SQL models attempt to translate a user's natural language question to corresponding SQL query. Recently, several generative text-to-SQL models have been developed.  ...  Bertrand AI is a suite of AI models developed by Got It Inc to tackle the text-2-SQL problem. The model described in this paper, Bertrand-DR, is part of that suite.  ... 
arXiv:2002.00557v2 fatcat:ljjoweja5zbsdgxjzeq2bwh4nm

IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation [article]

Yitao Cai, Xiaojun Wan
2020 arXiv   pre-print
Context-dependent text-to-SQL task has drawn much attention in recent years. Previous models on context-dependent text-to-SQL task only concentrate on utilizing historical user inputs.  ...  We evaluate our model on the benchmark SParC and CoSQL datasets, which are two large complex context-dependent cross-domain text-to-SQL datasets.  ...  This phenomenon brings difficulty for context-dependent text-to-SQL task. Recently, context-dependent text-to-SQL task has attracted more attention.  ... 
arXiv:2011.05744v1 fatcat:kkdn7ftxarckhh3pzlvgk3r6va

Linking-Enhanced Pre-Training for Table Semantic Parsing [article]

Bowen Qin, Lihan Wang, Binyuan Hui, Ruiying Geng, Zheng Cao, Min Yang, Jian Sun, Yongbin Li
2022 arXiv   pre-print
Recently pre-training models have significantly improved the performance of various NLP tasks by leveraging large-scale text corpora to improve the contextual representation ability of the neural network  ...  We further propose a schema-aware curriculum learning approach to mitigate the impact of noise and learn effectively from the pre-training data in an easy-to-hard manner.  ...  Lei et al. (2020) re-examined the role of schema linking in Text-to-SQL model.  ... 
arXiv:2111.09486v3 fatcat:h4kkm5arcrad3ef2tl4nwpoob4

Pay More Attention to History: A Context Modeling Strategy for Conversational Text-to-SQL [article]

Yuntao Li, Hanchu Zhang, Yutian Li, Sirui Wang, Wei Wu, Yan Zhang
2021 arXiv   pre-print
Conversational text-to-SQL aims at converting multi-turn natural language queries into their corresponding SQL representations.  ...  We conducted empirical studies and achieve new state-of-the-art results on large-scale open-domain conversational text-to-SQL dataset.  ...  Conversational Text-to-SQL Compared with single-turn text-to-SQL, conversational text-to-SQL requires semantic parsers to understand context of conversations to make correct SQL predictions.  ... 
arXiv:2112.08735v1 fatcat:56ec7mk2ajfdhixwa6by5csuvy

Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing [article]

Xi Victoria Lin and Richard Socher and Caiming Xiong
2020 arXiv   pre-print
Combined with a pointer-generator decoder with schema-consistency driven search space pruning, BRIDGE attained state-of-the-art performance on popular cross-DB text-to-SQL benchmarks, Spider (71.1% dev  ...  Our analysis shows that BRIDGE effectively captures the desired cross-modal dependencies and has the potential to generalize to more text-DB related tasks. Our implementation is available at .  ...  Our heartful thanks go to all who worked hard to keep others safe and enjoy a well-functioning life during this challenging time.  ... 
arXiv:2012.12627v2 fatcat:rfqrrkkuynbhxcthoda2af53qq

The history and recent advances of Natural Language Interfaces for Databases Querying

Khadija Majhadi, Mustapha Machkour, S. Krit
2021 E3S Web of Conferences  
One solution to this problem is to use Natural Language Interface (NLI), to communicate with the database, which is the easiest way to get information.  ...  However, the extraction of information stored in these databases is generally carried out using queries expressed in a computer language, such as SQL (Structured Query Language).  ...  RAT-SQL: RAT-SQL [35] is a centralized framework wish Based on the relation-aware schema encoding and linking for Text-to-SQL parsers that use a self-attention mechanism to direct schema encoding, schema  ... 
doi:10.1051/e3sconf/202122901039 fatcat:5mb6cxh4nfgo7dn5rpuar7wu5a

RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL [article]

Jiexing Qi, Jingyao Tang, Ziwei He, Xiangpeng Wan, Chenghu Zhou, Xinbing Wang, Quanshi Zhang, Zhouhan Lin
2022 arXiv   pre-print
However, introducing these structural relations comes with prices: they often result in a specialized model structure, which largely prohibits the use of large pretrained models in text-to-SQL.  ...  Relational structures such as schema linking and schema encoding have been validated as a key component to qualitatively translating natural language into SQL queries.  ...  Faced with the multi-table and complex SQL setting, using graph structures to encode a variety of complex relationships is a major trend in the text-to-SQL task.  ... 
arXiv:2205.06983v1 fatcat:tau5dylefja6fdzbtil2jgyu2y

Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing [article]

Ben Bogin, Matt Gardner, Jonathan Berant
2019 arXiv   pre-print
In Spider, a recently-released text-to-SQL dataset, new and complex DBs are given at test time, and so the structure of the DB schema can inform the predicted SQL query.  ...  Evaluation shows that encoding the schema structure improves our parser accuracy from 33.8% to 39.4%, dramatically above the current state of the art, which is at 19.7%.  ...  We review this model in the context of text-to-SQL parsing, focusing on components we expand upon in §4.  ... 
arXiv:1905.06241v2 fatcat:5mb6qcoma5aklhn4ytrfcdcnbe

Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing

Ben Bogin, Jonathan Berant, Matt Gardner
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
In SPIDER, a recentlyreleased text-to-SQL dataset, new and complex DBs are given at test time, and so the structure of the DB schema can inform the predicted SQL query.  ...  Evaluation shows that encoding the schema structure improves our parser accuracy from 33.8% to 39.4%, dramatically above the current state of the art, which is at 19.7%.  ...  Acknowledgments We thank Kevin Lin and Mark Neumann from Allen Institute for Artificial Intelligence for their help with the SQL grammar. This research was supported by Facebook.  ... 
doi:10.18653/v1/p19-1448 dblp:conf/acl/BoginBG19 fatcat:jj45i2lyrrcp3hmoxjot5dqe3q

RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers [article]

Bailin Wang, Richard Shin, Xiaodong Liu, Oleksandr Polozov, Matthew Richardson
2021 arXiv   pre-print
We present a unified framework, based on the relation-aware self-attention mechanism, to address schema encoding, schema linking, and feature representation within a text-to-SQL encoder.  ...  When translating natural language questions into SQL queries to answer questions from a database, contemporary semantic parsing models struggle to generalize to unseen database schemas.  ...  We thank Bo Pang, Tao Yu for their help with the evaluation. We also thank anonymous reviewers for their invaluable feedback.  ... 
arXiv:1911.04942v5 fatcat:3wyyhx4tsjbyxj5f3d6hhypk2m

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

Rui Zhang, Tao Yu, He Yang Er, Sungrok Shim, Eric Xue, Xi Victoria Lin, Tianze Shi, Caiming Xiong, Richard Socher, Dragomir Radev
2019 arXiv   pre-print
We focus on the cross-domain context-dependent text-to-SQL generation task.  ...  previous predicted query to improve the generation quality.  ...  In summary, SParC introduces new challenges to context-dependent text-to-SQL because it (1) contains more complex context dependencies, (2) has greater semantic coverage, and (3) adopts a crossdomain task  ... 
arXiv:1909.00786v2 fatcat:pcx4qqnckfbsjoums56d3i3bam
« Previous Showing results 1 — 15 out of 5,936 results