QAKiS addresses the task of QA over structured Knowledge Bases (e.g. DBpedia) where the relevant information is expressed also in unstructured form (e.g. Wikipedia pages). QAKiS allows end users to submit a query to an RDF triple store in English and obtain the answer in the same language, hiding the complexity of the non intuitive formal query languages involved in the resolution process. At the same time, the expressiveness of these standards is exploited to scale to the huge amounts of available semantic data. Its major novelty is to implement a relation-based match for question interpretation, to convert the user question into a query language (e.g. SPARQL).
English, French and German DBpedia chapters are the RDF data sets to be queried using a natural language interface.
The actual version of QAKiS targets questions containing a Named Entity related to the answer through one property of the ontology, as Which river does the Brooklyn Bridge cross?. Such questions match a single pattern, i.e., one relation.
Multimedia Answer visualization (NEW!) Beside the textual answer, QAKiS output embeds i) pictures from Wikipedia infoboxes, ii) OpenStreetMap, to visualize maps for questions asking about a place, and iii) YouTube, to visualize pertinent videos (e.g. movie trailers).
RADAR: ReconciliAtion of Dbpedia through ARgumentation framework (NEW!)The RADAR framework for information reconciliation has been integrated into QAKiS. The user can select the DBpedia chapter she wants to query besides English, i.e. French and German DBpedia. Then the user can either write a question or select among a list of examples, and click on Get Answers! Clicking on the tab RADAR, a graph with the answers provided by the different endpoints and the relations among them is shown to the user. Each node has an associated confidence score, resulting from the fuzzy labeling algorithm applied by RADAR. Moreover, each node is related to the others by a relation of support of attack, and a further specification of such relations according to the categories described in (Cabrio et al. LREC 2014) is provided to the user as answer justification of why the information items have been reconciled and ranked in this way.Beta versions: QAKiS 1.0 (previous version); With argumentation module (old) (Cabrio et al. ISWC-demo 2013)