Question Answering (QA) over Knowledge-Bases (KBs) is a very interesting research topic. A KB is a collection of facts. For example, DBpedia is a KB containing facts collected from Wikipedia like the birth date of persons, capitals of countries, museums in cities and many more. These facts are stored in machine readable formats and they can be retrieved using queries over databases. The information contained in such KBs can be very interesting for end-users, but we cannot require from them to write a formal query over a database (e.g. in SPARQL). This is where Question Answering over KBs comes into play, i.e. to automatically transform a natural language question like “Who is the mayor of Paris?” to a formal query that can be executed over a KB.

My research follows two directions. First, to create a framework, called Qanary, that allows to reuse and combine technologies that are already used in QA systems. This is done in collaboration with Andreas Both (Supervisor, Datev eG) and Kuldeep Singh (ESR 8, FRAUENHOFER). Second, considering the lessons learned from previous QA approaches, we are building a novel question answering system using new technologies. Currently it is enabled to query DBpedia, Wikidata, MusicBrainz (open music encyclopedia) and DBLP (computer science bibliography) using natural language questions and keywords. Moreover, it is possible to query Wikidata using English, French, German, Spanish and Italian. Visit it under www.wdaqua.eu/qa.

Started:
2015-06-01
Supervisors:

Publications

Towards a Message-Driven Vocabulary for Promoting the Interoperability of Question Answering Systems. Kuldeep Singh, Andreas Both, Dennis Diefenbach, Saeedeh Shekarpour. IEEE ICSC 2016: 386-389 URL PDF

Qanary - A Methodology for Vocabulary-driven Open Question Answering Systems. Andreas Both, Dennis Diefenbach, Kuldeep Singh, Saedeeh Shekarpour, Didier Cherix, Christoph Lange. ESWC 2016: 625-641 URL PDF

A Scalable Approach for Computing Semantic Relatedness using Semantic Web Data. Dennis Diefenbach, Ricardo Usbeck, Kamal Singh, Pierre Maret. WIMS 2016: 20:1-20:9 URL PDF

Qanary - the Fast Track to Creating a Question Answering System with Linked Data Technology. Kuldeep Singh, Andreas Both, Dennis Diefenbach, Saedeeh Shekarpour, Didier Cherix, Christoph Lange. ESWC (Satellite Events) 2016: 183-188 URL PDF

Computing the Semantic Relatedness of Music Genre using Semantic Web Data. Dennis Diefenbach, Pierre-René Lhérisson, Fabrice Muhlenbach, Pierre Maret. SEMANTiCS (Posters, Demos, SuCCESS) 2016 PDF

WDAqua-core0: A Question Answering Component for the Research Community. Dennis Diefenbach, Kamal Singh, Pierre Maret. ESWC, 7th Open Challenge on Question Answering over Linked Data (QALD-7) 2017 PDF

Trill: A generic Front-End for QA systems. Dennis Diefenbach, Shanzay Amjad, Andreas Both, Kamal Singh, Pierre Maret, ESWC P&D 2017 PDF

The Qanary Ecosystem: getting new insights by composing Question Answering pipelines. Dennis Diefenbach, Kuldeep Singh, Andreas Both, Didier Cherix, Christoph Lange,Sören Auer. ICWE 2017: 171-189 URL PDF

SPARQLtoUser: Did the question answering system understand me? Dennis Diefenbach, Youssef Dridi, Kamal Singh, Pierre Maret. BLINK/NLIWoD3@ISWC 2017 PDF

Question Answering Benchmarks for Wikidata. Dennis Diefenbach, Thomas Pellissier Tanon, Kamal Singh, Pierre Maret. International Semantic Web Conference (Posters, Demos & Industry Tracks) 2017 PDF

Core Techniques of Question Answering Systems over Knowledge Bases: a Survey. Dennis Diefenbach, Vanessa Lopez, Kamal Singh, Pierre Maret. Knowledge and Information Systems (2017) PDF

Rapid Engineering of QA Systems Using the Light-Weight Qanary Architecture. Andreas Both, Kuldeep Singh, Dennis Diefenbach, Ioanna Lytra. ICWE 2017: 544-548 URL PDF

Internship Students

(09/16-12/16) Shanzay Amjad : Designing a front-end for QA systems

(05/17-07/17) Youssef Dridi : Generating a user understandable representation of a SPARQL query

(05/17-07/17) Shanzay Amjad : Transform an industrial dataset in RDF to make QA on it