74,876 Hits in 4.7 sec

Explaining Causes Behind SQL Query Formulation Errors

Toni Taipalus
2020 2020 IEEE Frontiers in Education Conference (FIE)  
In order to more effectively teach query formulation, educators should emphasize natural language patterns, query planning, and increasingly ambiguous exercises.  ...  This Full Research Paper presents the most prominent query formulation errors in Structured Query Language (SQL), and maps these errors to their cognitive explanations.  ...  to the imperative nature of many programming languages studied [6] .  ... 
doi:10.1109/fie44824.2020.9274114 fatcat:hefky2uc45ei7klhitaw6qazhy

An intelligent approach to handling imperfect information in concept-based natural language queries

Vesper Owei
2002 ACM Transactions on Information Systems  
The approaches are specifically applied to the Conceptual Query Language with Natural Language (CQL/NL) that is presented in Owei [2000].  ...  In either case, the effect could be disastrous for organizations. In this article, therefore, approaches are developed for handling imperfection in concept-based natural language queries.  ...  Controlled Natural Language Filter in CQL/NL.  ... 
doi:10.1145/568727.568729 fatcat:u7223ub4bnhtlnym4gtzh565qy

Bio-SODA: Enabling Natural Language Question Answering over Knowledge Graphs without Training Data [article]

Ana Claudia Sima, Tarcisio Mendes de Farias, Maria Anisimova, Christophe Dessimoz, Marc Robinson-Rechavi, Erich Zbinden, Kurt Stockinger
2021 arXiv   pre-print
In particular, we introduce Bio-SODA, a natural language processing engine that does not require training data in the form of question-answer pairs for generating SPARQL queries.  ...  In this paper, we focus on the challenges of natural language processing over knowledge graphs of scientific datasets.  ...  Explainability in this context has therefore become an active area of research, with solutions proposed including translating back structured queries into natural language sentences [9, 21, 30] or summarizing  ... 
arXiv:2104.13744v4 fatcat:swbggfd34ng7fgh7qaiqokvxa4


Daniel Deutch, Nave Frost, Amir Gilad, Tomer Haimovich
2018 Proceedings of the VLDB Endowment  
Natural language (NL) interfaces to databases allow users without technical background to query the database and get the results.  ...  Our solution builds upon and combines recent advancements in Natural Language Interfaces to Databases and models for why-not provenance.  ...  The user is then presented with the results of the initial query along with natural language explanations for the result set tuples, generated by NLProv.  ... 
doi:10.14778/3229863.3236241 fatcat:e7zcnudicjbfjdj2ob4ovxr5n4

An End-to-end Neural Natural Language Interface for Databases [article]

Prasetya Utama, Nathaniel Weir, Fuat Basik, Carsten Binnig, Ugur Cetintemel, Benjamin Hättasch, Amir Ilkhechi, Shekar Ramaswamy, Arif Usta
2018 arXiv   pre-print
In this paper, we present DBPal, a novel data exploration tool with a natural language interface.  ...  DBPal leverages recent advances in deep models to make query understanding more robust in the following ways: First, DBPal uses a deep model to translate natural language statements to SQL, making the  ...  Exp. 1: Overall Results We evaluated the performance of all NLIDB systems in terms of their accuracy, defined as the number of natural language queries translated correctly over the total number of queries  ... 
arXiv:1804.00401v1 fatcat:hblzvhczajcmzi3suknmk6tuhy

AR2SPARQL: An Arabic Natural Language Interface for the Semantic Web

Iyad AlAgha, Alaa Abu-Taha
2015 International Journal of Computer Applications  
In the domain of English language, several efforts provided Natural Language (NL) interfaces to enable ordinary users to query ontologies using NL queries.  ...  With the growing interest in supporting the Arabic language on the Semantic Web (SW), there is an emerging need to enable Arab users to query ontologies and RDF stores without being challenged with the  ...  In the context of this work, we define a Natural Language (NL) interface as a system that accepts questions formulated in natural language and returns answers on the basis of a given knowledge base.  ... 
doi:10.5120/ijca2015905928 fatcat:r6zrvkxy4zaanlnhb52vw6mieq

Identifying SQL misconceptions of novices

Daphne Miedema, Efthimia Aivaloglou, George Fletcher
2022 ACM inroads  
The four reasons we found for mistakes are: interference of previous course knowledge, generalizing answers to questions where they do not fit, differences in language usage between SQL and natural language  ...  H ave you ever struggled with writing a SQL query to retrieve data? Students certainly do. In this paper we set out to investigate why this is the case.  ...  Question type Question ExecutionWhat is the result of Query 1? What is the Natural Language equivalent?11FormulationList all IDs & names of customers living in Eindhoven.  ... 
doi:10.1145/3514214 fatcat:cex2etgdxfgfdcds5zwfrmvbvi

Knowledge Graph Exploration: A Usability Evaluation of Query Builders for Laypeople [chapter]

Emil Kuric, Javier D. Fernández, Olha Drozd
2019 Lecture Notes in Computer Science  
The findings show that while WQS achieved the best results, usability problems were encountered in all tools.  ...  To counter this, specific tools have been created that enable more casual users to browse and query results.  ...  Screenshot of QueryVOWL query builder Natural Language-Based Query Builders. Natural language (NL) approaches offer users the convenient and valuable option of using natural language for querying.  ... 
doi:10.1007/978-3-030-33220-4_24 fatcat:aeh4mrmacrgr5bmprg5v6zhkje

Query expansion for Cross Language Information Retrieval Improvement

Benoit Gaillard, Jean-Leon Bouraoui, Emilie Guimier de Neef, Malek Boualem
2010 2010 Fourth International Conference on Research Challenges in Information Science (RCIS)  
This paper is devoted to a new method that uses query expansion to improve multilingual information retrieval.  ...  They also validate it with several measures, which show a clear reduction of the silence for results.  ...  To reach this aim, it provides search engines that enable users to enter a query in their own language, in order to retrieve lists of results in a different language.  ... 
doi:10.1109/rcis.2010.5507393 dblp:conf/rcis/GaillardBNB10 fatcat:kornsf46mbghbmccrz56bilxqy

The effects of information request ambiguity and construct incongruence on query development

A.Faye Borthick, Paul L. Bowen, Donald R. Jones, Michael Hung Kam Tse
2001 Decision Support Systems  
End users could translate natural language queries into pseudo-SQL that could be examined for precision before the queries were developed.  ...  The results for ambiguity suggest that organizations might elicit better query development if end users were sensitized to the nature of ambiguities that could arise in their business contexts.  ...  Ambiguity of information requests One problem in transforming a natural language request to an appropriate statement in the query language, i.e., of traversing the information requirement distance, is  ... 
doi:10.1016/s0167-9236(01)00097-5 fatcat:cjp36ibnynbftbj527lmeyhxwy

Expert Database System for Converting Unfit Query to Standard SQL Query

Laith R. Flaih
2017 Cihan University-Erbil Scientific Journal  
It is a fact that the DBMS is always strict in query execution that the unfit query for a simple reason would be rejected, this rejection affects communication momentum and user disappointment by not having  ...  The proposed system aims to prevent rejection of unfit query that is entered by the user through preparing it for optimization it so that it is in a simple correct form which is accepted by the DBMS.  ...  in another table after that correcting query and give a result to user. 3-Completing the incomplete query by adding the necessary missing keyword.  ... 
doi:10.24086/cuesj.v1n2a9 fatcat:zaon3qgznfaf3azmaz2xsipb2a

HAWK – Hybrid Question Answering Using Linked Data [chapter]

Ricardo Usbeck, Axel-Cyrille Ngonga Ngomo, Lorenz Bühmann, Christina Unger
2015 Lecture Notes in Computer Science  
These are executed so as to integrate the results of the text queries into SPARQL and thus generate a formal interpretation of the query.  ...  Our results show that HAWK achieves 0.68 respectively 0.61 F-measure within the training respectively test phases on the Question Answering over Linked Data (QALD-4) hybrid query benchmark.  ...  an in-depth analysis of the natural language input.  ... 
doi:10.1007/978-3-319-18818-8_22 fatcat:sczyjljcsfga3cf6vvrw2fcb54

DBPal: Weak Supervision for Learning a Natural Language Interface to Databases [article]

Nathaniel Weir, Andrew Crotty, Alex Galakatos, Amir Ilkhechi, Shekar Ramaswamy, Rohin Bhushan, Ugur Cetintemel, Prasetya Utama, Nadja Geisler, Benjamin Hättasch, Steffen Eger, Carsten Binnig
2019 arXiv   pre-print
data, which results in substantial overhead for supporting each new database schema.  ...  This paper describes DBPal, a new system to translate natural language utterances into SQL statements using a neural machine translation model.  ...  Exp. 1: Overall Results We evaluated the performance of all NLIDB systems in terms of their accuracy, defined as the number of natural language queries translated correctly over the total number of queries  ... 
arXiv:1909.06182v1 fatcat:gvoe4rtymfesdpeqlbmj7xlgii

Initial Implementation of Natural Language Turn-Based Dialog System

Alexander Wachtel, Sebastian Weigelt, Walter F. Tichy
2016 Procedia Computer Science  
JustLingo 1 allows spreadsheet calculations in ordinary, written English. Furthermore, users can extend the system functionality by explaining of the calculations to the prototype.  ...  Our prototype implements a natural language dialog system for Excel spreadsheets.  ...  Individual modules are explained in the order in which they generate output that leads to a valid final result.  ... 
doi:10.1016/j.procs.2016.04.065 fatcat:2ln3e6eglzbjposv4pprmk2v64

A general language model for information retrieval

Fei Song, W. Bruce Croft
1999 Proceedings of the eighth international conference on Information and knowledge management - CIKM '99  
According to this new paradigm, each document is viewed as a language sample, and a query as a generation process.  ...  The retrieved documents are ranked based on the probabilities of producing a query from the corresponding language models of these documents.  ...  Any opinions, findings and conclusions or recommendations expressed in this paper are the authors and do not necessarily reflect those of the sponsors.  ... 
doi:10.1145/319950.320022 dblp:conf/cikm/SongC99 fatcat:7m6ehvpuojan7lbft6n43nt35i
« Previous Showing results 1 — 15 out of 74,876 results