A demo of PowerAqua is available at http://technologies.kmi.open.ac.uk/poweraqua/demo-poweraqualinked.mp4
The types of queries that can be answered in PowerAqua are factual queries that can be represented by one or more linguistic triples, where this triple represents and explicit or implicit relationship between two terms. The linguistic triple is only a formal, simplified way of representing the NL-query, and therefore it can be translated into one or more ontological triples in the same or different ontologies.
This includes all the big set of queries constituted by a wh-question, such as the ones starting with: what, who, when, where, are there any, does anybody/anyone or how many, etc. Also imperative commands like list, give, tell, name, etc; are treated as wh-queries (see the example table and templates bellow). In fact, wh-queries are categorized by PowerAqua depending on its equivalent intermediate representation. For example, in "who are the academics involved in the semantic web?" the generic triple will be of the form <generic term, relation, second term>, in our example <academics, involved, semantic web>. Whereas in other queries either the relation is implicit or unknown, like in "are there any phd students in akt?" where the equivalent representation is <phd students, ?, akt>, or they provide little or no information about the type of the expected answer, e.g. "what is the job title of John?", or they can be just a generic enquiry about someone or something, e.g. "who is Vanessa?", "what is an ontology?"
Currently PowerAqua is not able to answer:
- Queries requiring temporal (i.e. recently, in the last year), or casual (why - type of queries) reasoning
- Note that titles or names separated by prepositions should be quoted, e.g. "Who wrote "Alicia in wonderland"?", or "Who works in the "university of Zaragoza""?
- Queries that contain negations (i.e. do not, never), or that require to perform any kind of ranking, comparatives or superlatives (i.e., the most, same as, the biggest, the fastest, the best, the less, etc) or proportions/percentages (i.e "what is the percentage of the population [...]?")