文章基本信息

标题：Answering End-User Questions, Queries and Searches on Wikipedia and its History
本地全文：下载
作者：Maurizio Atzori ; Shi Gao ; Giuseppe M. Mazzeo 等
期刊名称：Bulletin of the Technical Committee on Data Engineering
出版年度：2016
卷号：39
期号：3
页码：85
出版社：IEEE Computer Society
摘要：Knowledge bases (KBs) encoded using RDF triples deliver many benefits to applications and program-mers that access the KBs on the web via SPARQL endpoints. In this paper, we describe and comparetwo user-friendly systems that seek to make the universal knowledge of Web KBs available to userswho neither know SPARQL, nor the internals of the KBs. We first describe CANaLI, that lets peopleenter Natural Language (NL) questions and translates them into SPARQL queries executed on DBpe-dia. CANaLI removes the ambiguities that are often present in NL communication by requiring the useof a Controlled NL and providing on-line knowledge-driven question-completion that shows alternatecorrect interpretations. While CANaLI is a very powerful NL system, which placed first in the 2016 com-petition on Question Answering over Linked Data QALD-6, even more powerful user-friendly interfacesare available to users who enter questions and queries on web-browsers. In particular, the SWiPE sys-tem provides a wysiwyg interface that lets users specify powerful queries on the Infoboxes of Wikipediapages in a query-by-example fashion. Thus, in addition to those supported in CANaLI, we now havequeries with (i) complex aggregates, (ii) structured conditions combined with keyword-based searches,and (iii) temporal conditions on Cliopedia, a historical knowledge base that captures the evolution ofWikipedia entities and properties. These systems demonstrate that semi-curated web document corporaand their KBs are making possible the seamless integration through user-friendly interfaces of (i) NLquestion answering, (ii) structured DB queries, and (iii) information retrieval. These were once viewedas distinct functions supported by different enabling technologies.