We present QAKiS, a system for Question Answering over linked data (in particular, DBpedia). The problem of question interpretation is addressed as the automatic identification of the set of relevant relations between entities in the natural language input question, matched against a repository of automatically collected relational patterns (i.e. the WikiFramework repository). Such patterns represent possible lexicalizations of ontological relations, and are associated to a SPARQL query derived from the linked data relational patterns. Wikipedia is used as the source of free text for the automatic extraction of the relational patterns, and DBpedia as the linked data resource to provide relational patterns and to be queried using a natural language interface.
We present QAKiS, a system for Question Answering over linked data (in particular, DBpedia). The problem of question interpretation is addressed as the automatic identification of the set of relevant relations between entities in the natural language input question, matched against a repository of automatically collected relational patterns (i.e. the WikiFramework repository). Such patterns represent possible lexicalizations of ontological relations, and are associated to a SPARQL query derived from the linked data relational patterns. Wikipedia is used as the source of free text for the automatic extraction of the relational patterns, and DBpedia as the linked data resource to provide relational patterns and to be queried using a natural language interface.
QAKiS @ QALD-2 / Cabrio, Elena; Palmero Aprosio, Alessio; Cojan, Julien; Magnini, Bernardo; Gandon, Fabien; Lavelli, Alberto. - 913:(2012), pp. 87-95. ( Workshop on Interacting with Linked Data 2012, ILD 2012 - Workshop Co-located with the 9th Extended Semantic Web Conference Heraklion, Greece May 28, 2012).
QAKiS @ QALD-2
Cabrio, Elena;Palmero Aprosio, Alessio;Magnini, Bernardo;Lavelli, Alberto
2012-01-01
Abstract
We present QAKiS, a system for Question Answering over linked data (in particular, DBpedia). The problem of question interpretation is addressed as the automatic identification of the set of relevant relations between entities in the natural language input question, matched against a repository of automatically collected relational patterns (i.e. the WikiFramework repository). Such patterns represent possible lexicalizations of ontological relations, and are associated to a SPARQL query derived from the linked data relational patterns. Wikipedia is used as the source of free text for the automatic extraction of the relational patterns, and DBpedia as the linked data resource to provide relational patterns and to be queried using a natural language interface.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
