• Corpus ID: 15733683

Answering End-User Questions, Queries and Searches on Wikipedia and its History

  title={Answering End-User Questions, Queries and Searches on Wikipedia and its History},
  author={Maurizio Atzori and Shi Gao and Giuseppe M. Mazzeo and Carlo Zaniolo},
  journal={IEEE Data Eng. Bull.},
Knowledge bases (KBs) encoded using RDF triples deliver many benefits to applications and programmers that access the KBs on the web via SPARQL endpoints. In this paper, we describe and compare two user-friendly systems that seek to make the universal knowledge of Web KBs available to users who neither know SPARQL, nor the internals of the KBs. We first describe CANaLI, that lets people enter Natural Language (NL) questions and translates them into SPARQL queries executed on DBpedia. CANaLI… 

Figures and Tables from this paper

Question Answering on RDF KBs using Controlled Natural Language and Semantic

In experiments conducted on well-known QA benchmarks, including questions on the encyclopedic DBpedia and on KBs from specialized domains, such as music and medicine, CANaLI typically outperforms other QA systems.

A survey on semantic question answering systems

This paper analyses different frameworks, architectures, or systems that perform SQA and classifies SQA systems based on different criteria.

Keyword Search on RDF Graphs - A Query Graph Assembly Approach

This paper formally defines the query graph assembly (QGA) problem, design some heuristic lower bounds and propose a bipartite graph matching-based best-first search algorithm, which has good scalability in large RDF graphs.

The Need of Structured Data: Introducing the OKgraph Project

This position paper argues that in the case of Information Retrieval tasks this is not mandatory and even detrimental whenever alternatives exist, and suggests to split the problem into two sub-problems: producing structured data out of the corpora, and providing usable tools to querying such structured data.

Fixing Wikipedia Interlinks Using Revision History Patterns

The WICLEAN (WC) system is presented, which identifies relevant edit patterns across revision histories of Wikipedia entities of related types, along with time windows in which partial edits are tolerable and is used to alert Wikipedia editors on past edits that appear to be incomplete.

qb : Dataset qb : Observation qb : dataset dimensionValue dimensionProperty measureValue attributeValue attributeProperty measureProperty

QA3, a question answering (QA) system over RDF data cubes, first tags chunks of text with elements of the knowledge base, and then leverages the well-defined structure of data cubes to create a SPARQL query from the tags.



Answering Controlled Natural Language Questions on RDF Knowledge Bases

This work presents a Question Answering (QA) system that accepts questions posed in a Controlled Natural Language, and an ontology driven autocompletion system displays suggested patterns computed in real time from the partially completed sentence the person is typing.

SPARQLT and its User-Friendly Interface for Managing and Querying the History of RDF Knowledge Bases

This paper introduces SPARQL and its user-friendly interface for expressing powerful structured queries on the history of RDF knowledge bases, and overviews its underlying query engine that supports efficient evaluation of such queries and the management of historical information.

Expressivity and Accuracy of By-Example Structured Queries on Wikipedia

  • M. AtzoriC. Zaniolo
  • Computer Science
    2015 IEEE 24th International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises
  • 2015
The experiments show that SWiPE outperforms the results provided by Wikipedia, and it also performs sensibly better than Xser, obtaining an overall 85% of totally correct answers vs. 68% of Xser.

SWiPE: searching wikipedia by example

Swipe's SBE approach makes semi-structured documents queryable in an intuitive and user-friendly way and, through Wikipedia, delivers the benefits of querying and exploring large knowledge bases to all Web users.

Natural language question answering over RDF: a graph data driven approach

A semantic query graph is proposed to model the query intention in the natural language question in a structural way, based on which, RDF Q/A is reduced to subgraph matching problem and resolves the ambiguity of natural language questions at the time when matches of query are found.

Answering Natural Language Questions with Intui3

The system accepts as input a question formulated in natural language (in English), and uses syntactic and semantic information to construct its interpretation with respect to a given database of RDF triples (in this case DBpedia 3.9).

Schema-free structured querying of DBpedia data

This work describes a compromise in which non-experts specify a graphical query "skeleton" and annotate it with freely chosen words, phrases and entity names that reduces ambiguity and allows the generation of an interpretation that can be translated into SPARQL.

Supporting semantic web search and structured queries on mobile devices

This paper proposes a novel mobile interface that allows both browsing and querying the Semantic Web without using sparql nor knowledge of the underlying ontology/schema of the supporting knowledge base, and develops QPedia1, a mobile app that allows to take full advantages of DBpedia through the mobile-enabled user-friendly interface.

A HMM-based Approach to Question Answering against Linked Data

A QA system enabling NL questions against Linked Data, designed and adopted by the Tor Vergata University AI group in the QALD-3 evaluation, and exploits a graphical model to select the proper ontological triples according to the graph nature of RDF.