NLProveNAns: Natural language provenance for non-answers

Daniel Deutch, Nave Frost, Amir Gilad, Tomer Haimovich

Research output: Contribution to journalConference articlepeer-review

7 Scopus citations

Abstract

Natural language (NL) interfaces to databases allow users without technical background to query the database and get the results. Users of such systems may be surprised by the absence of certain expected results. To this end, we propose to demonstrate NLProveNAns, a system that allows non-expert users to view explanations for non-answers of interest. The explanations are shown in an intuitive manner, by highlighting parts of the original NL query that are intuitively “responsible“ for the absence of the expected result. Our solution builds upon and combines recent advancements in Natural Language Interfaces to Databases and models for why-not provenance. In particular, the systems can provide explanations in one of two avors corresponding to two different why-not provenance models: a short explanation based on the frontier picky model, and a detailed explanation based on the why-not polynomial model.

Original languageEnglish
Pages (from-to)1986-1989
Number of pages4
JournalProceedings of the VLDB Endowment
Volume11
Issue number12
DOIs
StatePublished - 1 Jan 2018
Externally publishedYes
Event44th International Conference on Very Large Data Bases, VLDB 2018 - Rio de Janeiro, Brazil
Duration: 27 Aug 201831 Aug 2018

Fingerprint

Dive into the research topics of 'NLProveNAns: Natural language provenance for non-answers'. Together they form a unique fingerprint.

Cite this