Explaining Natural Language query results

Daniel Deutch, Nave Frost, Amir Gilad*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

12 Scopus citations


Multiple lines of research have developed Natural Language (NL) interfaces for formulating database queries. We build upon this work, but focus on presenting a highly detailed form of the answers in NL. The answers that we present are importantly based on the provenance of tuples in the query result, detailing not only the results but also their explanations. We develop a novel method for transforming provenance information to NL, by leveraging the original NL query structure. Furthermore, since provenance information is typically large and complex, we present two solutions for its effective presentation as NL text: one that is based on provenance factorization, with novel desiderata relevant to the NL case and one that is based on summarization. We have implemented our solution in an end-to-end system supporting questions, answers and provenance, all expressed in NL. Our experiments, including a user study, indicate the quality of our solution and its scalability.

Original languageEnglish
Pages (from-to)485-508
Number of pages24
JournalVLDB Journal
Issue number1
StatePublished - 1 Jan 2020


FundersFunder number
European Union’s Horizon 2020 research and innovation programme
Google Ph.D.
Israeli Science Foundation978/17
Horizon 2020 Framework Programme804302
European Research Council
Israel Science Foundation


    • CQ
    • NL
    • Natural Language
    • Provenance
    • UCQ


    Dive into the research topics of 'Explaining Natural Language query results'. Together they form a unique fingerprint.

    Cite this