Asking Data in a Controlled Way with Ask Data Anything NQL - Publikacja - MOST Wiedzy

Wyszukiwarka

Asking Data in a Controlled Way with Ask Data Anything NQL

Abstrakt

While to collect data, it is necessary to store it, to understand its structure it is necessary to do data-mining. Business Intelligence (BI) enables us to make intelligent, data-driven decisions by the mean of a set of tools that allows the creation of a potentially unlimited number of machine-generated, data-driven reports, which are calculated by a machine as a response to queries specified by humans. Natural Query Languages (NQLs) allow one to dig into data with an intuitive human-machine dialogue. The current NQL-based systems main problems are the required prior learning phase for writing correct queries, understanding the linguistic coverage of the NQL and asking precise questions. Results: We have developed an NQL as well as an entire Natural Language Interface Database (NLIDB) that supports the user with BI queries with minimized disadvantages, namely Ask Data Anything. The core part - NQL parser - is a hybrid of CNL and the pattern matching approach with a prior error repair phase. Equipped with reasoning capabilities due to the intensive use of semantic technologies, our hybrid approach allows one to use very simple, keyword-based (even erroneous) queries as well as complex CNL ones with the support of a predictive editor. Supplementary Information: Supplementary materials a

Cytowania

  • 0

    CrossRef

  • 0

    Web of Science

  • 0

    Scopus

Autorzy (6)

Cytuj jako

Pełna treść

pełna treść publikacji nie jest dostępna w portalu

Słowa kluczowe

Informacje szczegółowe

Kategoria:
Aktywność konferencyjna
Typ:
materiały konferencyjne indeksowane w Web of Science
Tytuł wydania:
Controlled Natural Language strony 58 - 68
ISSN:
0302-9743
Język:
angielski
Rok wydania:
2016
Opis bibliograficzny:
Seganti A., Kapłański P., Campo J., Cieśliński K., Koziołkiewicz J., Zarzycki P..: Asking Data in a Controlled Way with Ask Data Anything NQL, W: Controlled Natural Language, 2016, Springer,.
DOI:
Cyfrowy identyfikator dokumentu elektronicznego (otwiera się w nowej karcie) 10.1007/978-3-319-41498-0_6
Weryfikacja:
Politechnika Gdańska

wyświetlono 109 razy

Publikacje, które mogą cię zainteresować

Meta Tagi