Filters








4,055 Hits in 4.8 sec

Global Reasoning over Database Structures for Text-to-SQL Parsing [article]

Ben Bogin, Matt Gardner, Jonathan Berant
2019 arXiv   pre-print
In this work, we propose a semantic parser that globally reasons about the structure of the output query to make a more contextually-informed selection of database constants.  ...  We apply our techniques to the current state-of-the-art model for Spider, a zero-shot semantic parsing dataset with complex databases, increasing accuracy from 39.4% to 47.4%.  ...  Acknowledgments This research was partially supported by The Yandex Initiative for Machine Learning. This work was completed in partial fulfillment for the Ph.D degree of the first author.  ... 
arXiv:1908.11214v1 fatcat:o52ssrl5jrawbmod7bnash7tru

Global Reasoning over Database Structures for Text-to-SQL Parsing

Ben Bogin, Matt Gardner, Jonathan Berant
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
In this work, we propose a semantic parser that globally reasons about the structure of the output query to make a more contextuallyinformed selection of database constants.  ...  We apply our techniques to the current state-ofthe-art model for SPIDER, a zero-shot semantic parsing dataset with complex databases, increasing accuracy from 39.4% to 47.4%.  ...  Acknowledgments This research was partially supported by The Yandex Initiative for Machine Learning. This work was completed in partial fulfillment for the Ph.D degree of the first author.  ... 
doi:10.18653/v1/d19-1378 dblp:conf/emnlp/BoginGB19 fatcat:xsfwd3ub65fudhupnhe3iumcla

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
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 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.  ...  We also thank anonymous reviewers for their invaluable feedback.  ... 
arXiv:1911.04942v5 fatcat:3wyyhx4tsjbyxj5f3d6hhypk2m

A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing [article]

Sanxing Chen, Aidan San, Xiaodong Liu, Yangfeng Ji
2020 arXiv   pre-print
In Text-to-SQL semantic parsing, selecting the correct entities (tables and columns) for the generated SQL query is both crucial and challenging; the parser is required to connect the natural language  ...  (NL) question and the SQL query to the structured knowledge in the database.  ...  Acknowledgments We thank Yu Bai and members of the UVA NLP group for valuable discussion and feedback. We also thank all anonymous reviewers for their helpful comments and suggestions.  ... 
arXiv:2009.14809v2 fatcat:45u23r7mrjazrfmw5cub3n3gra

Epi Archive: Automated Synthesis of Global Notifiable Disease Data

Hari S. Khalsa, Sergio Cordova, Nicholas Generous, Prabhu S. Khalsa, Byron Tasseff, James Arnold
2018 Online Journal of Public Health Informatics  
We store all artifacts presented as files (PDF, XLSX, etc.) in their original form, along with appropriate metadata for parsing and data provenance.Detecting: This step is required when parsing structured  ...  format, governments are often hesitant to share data openly for a variety of reasons that include technical, political, economic, and motivational issues1.A survey conducted by LANL of notifiable disease  ...  Persisting: We store the data in the Epi Archive database and make it available on the internet and through the BSVE. The data is persisted into a structured and normalized SQL database.  ... 
doi:10.5210/ojphi.v10i1.8323 fatcat:2jbntk7nhba4znohjyerqugc5a

Relation Aware Semi-autoregressive Semantic Parsing for NL2SQL [article]

Junyang Huang, Yongbo Wang, Yongliang Wang, Yang Dong, Yanghua Xiao
2021 arXiv   pre-print
Natural language to SQL (NL2SQL) aims to parse a natural language with a given database into a SQL query, which widely appears in practical Internet applications.  ...  To solve the challenging task, we present a Relation aware Semi-autogressive Semantic Parsing (\MODN) ~framework, which is more adaptable for NL2SQL.  ...  RAT-SQL (Wang et al., 2020a) and DT-Fixup (Xu et al., 2020) encode relational structure in the database schema and a given question using relation-aware self-attention to combine global reasoning over  ... 
arXiv:2108.00804v1 fatcat:43vwysanprhfnnhwloiby7jqoe

SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL [article]

Ruichu Cai, Jinjie Yuan, Boyan Xu, Zhifeng Hao
2022 arXiv   pre-print
Focusing on the above two key issues, we propose a Structure-Aware Dual Graph Aggregation Network (SADGA) for cross-domain Text-to-SQL.  ...  One of the most challenging problems of Text-to-SQL is how to generalize the trained model to the unseen database schemas, also known as the cross-domain Text-to-SQL task.  ...  Acknowledgements We thank Tao Yu and Yusen Zhang for their evaluation of our work in the Spider Challenge. We also thank the anonymous reviewers for their helpful comments.  ... 
arXiv:2111.00653v3 fatcat:znwo4wg2vnhbzle4yr3oninaze

Rule-Based Impact Analysis for Enterprise Business Intelligence [chapter]

Kalle Tomingas, Tanel Tammet, Margus Kliimask
2014 IFIP Advances in Information and Communication Technology  
Case studies are employed to explain further data aggregation and visualization of the results to address different planning and decision support problems for various user profiles like business users,  ...  The paper presents practical methods to calculate meaningful data transformation and component dependency paths, based on program parsing, heuristic impact analysis, probabilistic rules and semantic technologies  ...  The Parse Tree Mapper (No3 in ctio- and ase. the and the nner have rces e to sys- ions ripts ored the res- ruc- the text As SQL d to we  ... 
doi:10.1007/978-3-662-44722-2_32 fatcat:w3qspxxvwfdgtn5erptosdsolu

GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing [article]

Tao Yu and Chien-Sheng Wu and Xi Victoria Lin and Bailin Wang and Yi Chern Tan and Xinyi Yang and Dragomir Radev and Richard Socher and Caiming Xiong
2021 arXiv   pre-print
We construct synthetic question-SQL pairs over high-quality tables via a synchronous context-free grammar (SCFG) induced from existing text-to-SQL datasets.  ...  We pre-train our model on the synthetic data using a novel text-schema linking objective that predicts the syntactic role of a table field in the SQL for each question-SQL pair.  ...  In our work, we formulate text-to-SQL as a multi-class classification task for each column, which can be naturally combined with the MLM objective to pre-train BERT for semantic parsing.  ... 
arXiv:2009.13845v2 fatcat:dzy5bu2cbna2lg7m6zun4lavhm

Frameworks for Querying Databases Using Natural Language: A Literature Review [article]

Hafsa Shareef Dar, M.Ikramullah Lali, Moin Ul Din, Khalid Mahmood Malik, Syed Ahmad Chan Bukhari
2019 arXiv   pre-print
A Natural Language Interface (NLI) facilitates users to pose queries to retrieve information from a database without using any artificial language such as the Structured Query Language (SQL).  ...  To best of our knowledge, there is no recent study found which discusses the current state of the art translations frameworks for natural language for structured and non-structured query languages.  ...  In this survey paper, we have reviewed Natural language to database querying frameworks developed for both the structured (SQL) and non-structured database query languages (NoSQL, GraphDB).  ... 
arXiv:1909.01822v1 fatcat:brhl73u3jjbx3owfalmpiaopcm

Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model

Juntao Li, Ruidan He, Hai Ye, Hwee Tou Ng, Lidong Bing, Rui Yan
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
Recent research indicates that pretraining cross-lingual language models on large-scale unlabeled texts yields significant performance improvements over various cross-lingual and low-resource tasks.  ...  Through training on one hundred languages and terabytes of texts, cross-lingual language models have proven to be effective in leveraging high-resource languages to enhance low-resource language processing  ...  decoding network with recursive mechanism; Global GNN reasons over the DB structure and questions to make global decision; EditSQL proposes an editing mechanism-based network; and IRNET uses schema linking  ... 
doi:10.24963/ijcai.2020/504 dblp:conf/ijcai/Zeng0GCLLTZ20 fatcat:3uyhucybkzb35objwppqer4auq

SQLProb

Anyi Liu, Yi Yuan, Duminda Wijesekera, Angelos Stavrou
2009 Proceedings of the 2009 ACM symposium on Applied Computing - SAC '09  
SQLProb harnesses the effectiveness and adaptivity of genetic algorithms to dynamically detect and extract users' inputs for undesirable SQL control sequences.  ...  To curtail the attackers' ability to generate such attacks, we propose an SQL Proxy-based Blocker (SQLProb).  ...  ACKNOWLEDGEMENTS We thank William Halfond and Alex Orso for providing SQL injection application testbed.  ... 
doi:10.1145/1529282.1529737 dblp:conf/sac/LiuYWS09 fatcat:bhd6ggwvfjcwthqycmdaidz5ti

Framework of SQL Injection Attack [article]

Neha Patwari, Parvati Bhurani
2012 arXiv   pre-print
Hence a dynamic algorithm is given in this paper for preventing SQL Injection Attacks which is based on context free grammars and compiler parsing techniques.  ...  The paper attempts to present the notation of a SQLI Prevent Parser for the prevention of SQL Injection Attacks.  ...  Approach The developer built a data structure for the parsed representation of the statement, which is called a parser. For parsing, we require the grammar language of statement.  ... 
arXiv:1207.1542v1 fatcat:blqvmbh2czfhnk5adniwvruqw4

AppSleuth

Wei Cao, Dennis Shasha
2013 Proceedings of the 16th International Conference on Extending Database Technology - EDBT '13  
We present a tool called AppSleuth that parses application code and the tracing log for two popular database management systems in order to lead a competent tuner to the hot spots in an application.  ...  display to give a global view of the issue.  ...  ACKNOWLEDGEMENTS We would like to thank Laura Puglisi for helpful discussions as well as both the conference reviewers and our shepherd for their thoughtful comments.  ... 
doi:10.1145/2452376.2452445 dblp:conf/edbt/CaoS13 fatcat:icx6nzwehfb7nmsbdc6fh3rc74

Design and implementation of heterogeneous distributed multimedia system using mosaic GSQL

Sunil Magavi, Johnny Wong, Prakash Bodla
1995 Software, Practice & Experience  
This project explores one of the possibilities for providing an integrated system to the user to access the different types of media like text, image, audio and video stored in different databases on remote  ...  We have used the National Center for Supercomputer Applications (NCSA) Mosaic's Gateway Structured Query Language (GSQL), which enables a system developer to build input forms, query to the remote database  ...  This now waits for the client to send the SQL statements over the network using TCP/IP. 3.  ... 
doi:10.1002/spe.4380251104 fatcat:nmnmpbt4ifafjoujcnw55y4f44
« Previous Showing results 1 — 15 out of 4,055 results