Constructing an interactive natural language interface for relational databases

Li, Fēi; Jagadish, H. V.

doi:10.14778/2735461.2735468

Cited by 389 publications

(332 citation statements)

References 22 publications

Supporting

Mentioning

327

Contrasting

Unclassified

Order By: Relevance

“…For instance, the work proposed by Li et al [42] discusses an approach developed to analyze users requests, not necessarily expressed in question format. Stanford Dependency parser and similarity functions were used to map words into database tables and columns.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…We also handle fuzzy requests and aggregation functions which are features that the approach of Li et al [42] lacks. Table 2.3 includes a detailed comparison between our approach and that of Li et al [42]. Another approach that analyzes user questions to retrieve data from relational databases was proposed by Giordani et al [28].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Integrating flexibility and fuzziness into a question driven query model

Sarhan

Rokne

Alhajj

2018

Information Sciences

View full text Add to dashboard Cite

Data plays an important role in our daily life. Thus, data collection, storage, maintenance and processing continue to attract considerable attention. Data may exist in various formats, ranging from unstructured to structured as the two extremes. Traditionally, researchers and practitioners cooperated and developed various data models which form the main foundation for existing database management systems. The relational data model is still dominating despite the rapid development in the techniques used for data collection, storage and processing. Further, a relational database management system supports a structured query language (SQL) for data processing, and it is not possible to access and retrieve data from a relational database without knowing how to use SQL. However, the wide usage of relational databases motivated researchers to develop more user friendly interfaces which would allow a larger population of users to access relational databases. Such interfaces range from visual to natural language based. This thesis contributes a question driven query model which falls under the natural language based category. The target is to make databases reachable by a larger population, especially after the Internet increased database availability. The proposed model supports fuzziness where every user is given the freedom to define his/her own understanding of fuzzy terms. The developed system absorbs the fuzzy understanding of each user to utilize it while deciding on the result to be communicated back as answer to the raised question. Data mining techniques are employed to guide users in defining their fuzzy understanding. The developed model is intended to help users to retrieve the data they want from a relational database without expecting them to know SQL. In the current version only questions written in English are allowed. The system handles different types of questions, such as (1) simple questions, (2) complex questions with inner joins and where conditions, (3) questions that involves the usage of aggregate functions (e.g., min, max, etc.), and (4) questions with fuzzy i terms. The reported test results demonstrate the effectiveness of the developed system in handling various types of questions raised by a heterogeneous set of users ranging from professionals to naive.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Integrating flexibility and fuzziness into a question driven query model

Sarhan

Rokne

Alhajj

2018

Information Sciences

View full text Add to dashboard Cite

show abstract

“…Also, Ayan et al [13] proposed a technique "Clarifying natural language input using targeted questions" that used some predefined questions for understanding the natural language input from the user and hence provided suitable results. Llopis et al [14] provided an example for creating a natural language interface to query a database. The authors explain different constraints and data structures used for creating this interface.…”

Section: Related Workmentioning

confidence: 99%

SDRED: Smart Data Retrieval Engine for Databases

Ahmad¹,

Zahra²

2018

IJITCS

View full text Add to dashboard Cite

Abstract-Today computers are continuously betrothed in almost all domains and organizations. Thus, databases act as the heart for storing and retrieving information that contain huge digital data. However, in order to interact with such databases, it is necessary to have knowledge about the Structured Query Language (SQL), which is difficult for non-expert users to understand and manipulate. So, there is an emergent need to develop a smart and a user friendly computational technique to interact with databases. The current work proposed a smart technique that can handle such context. The proposed "Smart Data Retrieval Engine for Databases (SDRED)" provided an environment that allows a nonexpert user to write and to execute the database queries easily. Furthermore, it retrieved the data stored in databases without a prior knowledge of the SQL. SDRED, which enables the non-expert user to write database queries in natural language (such as English) and to convert them to their SQL query equivalents. The current work presented a detailed design and evaluation for the proposed system by executing different database queries in English. The results established that SDRED successfully converted the non-expert user's natural language queries into their equivalent SQL queries, thereby providing an easy and user-friendly environment to interact with databases.

show abstract

“…But in multidimensional data store area, many efforts such as SPARQLGraph [5] can be seen as domain-specific methodology. NaLIR [6,7] now can accept a logically complex English language sentence as query input for data store, but there is still a long way to take natural language queries as a database query interface due to the difficulty of multilingual user-specified query translation into the actual schema structure in the multidimensional data store.…”

Section: Related Workmentioning

confidence: 99%

ViMDQL: An Easy-to-Use Drag-and-Drop Visual Query Composer for Multidimensional Data

2017

JWSA

View full text Add to dashboard Cite

Abstract. In this study, we present ViMDQL, a useful system to tack the challenge of composing multidimensional data based analytical queries easily. Currently, fundamental query blocks such as import and export, create, retrieve, update, delete are supported, which can be used to loading and exporting data, creating, retrieving, updating, join, sampling and removing multidimensional data. Analytic functionalities such as aggregation, statistics are also supported. We demonstrated that, since ViMDQL make users can express their query intent by drag and drop to link query blocks together, which enable users can easily compose queries like the Stacker Game, it has been proved to be a productivity tool for graphically building multidimensional data based queries.

show abstract

Constructing an interactive natural language interface for relational databases

Cited by 389 publications

References 22 publications

Integrating flexibility and fuzziness into a question driven query model

Integrating flexibility and fuzziness into a question driven query model

SDRED: Smart Data Retrieval Engine for Databases

ViMDQL: An Easy-to-Use Drag-and-Drop Visual Query Composer for Multidimensional Data

Contact Info

Product

Resources

About