- From: Paola Di Maio <paola.dimaio@gmail.com>
- Date: Wed, 18 Jan 2023 22:24:05 +0800
- To: Contact - Cogsonomy <contact@cogsonomy.fr>
- Cc: Semantic Web <semantic-web@w3.org>, W3C AIKR CG <public-aikr@w3.org>
- Message-ID: <CAMXe=Srb+fC_xos0V0ca0rt9wVyC6u+wpM+kcrz_zgmE8ZyCgQ@mail.gmail.com>
in fact, I suspect the sparql could be made invisible or even it may already be implicitly hidden in the tool (my guess) and users would not know (which may be a good thing unless users want to dig further how/where the source data comes from or test the result agains the kbase) but to learn sparql, or to check it, or to refine the query, or to check and compare query outputs from different repos, yes, great functionality to have, thanks On Wed, Jan 18, 2023 at 10:15 PM Paola Di Maio <paola.dimaio@gmail.com> wrote: > assuming the syntax is good > (your example validates here http://sparql.org/$/validate/query) > then it looks like a big YES > It would be amazing to have a tool that can translate natural language > queries into sparql > and remove a major hurdle to using open ontologies on the web > Please, lets set up a catalogue of examples and evaluate the results > great functionality if it works > thank you > > > On Tue, Jan 17, 2023 at 10:41 PM Contact - Cogsonomy <contact@cogsonomy.fr> > wrote: > >> Hi, >> >> I asked chatGPT to create a sparql query for DBPedia by translating my >> question expressed in natural language : "Give me all the names of the >> cities located in France whose number of inhabitants is greater than >> 10,000". >> >> Its answer was as follows : >> >> *here's the SPARQL query to answer the question:* >> >> *PREFIX dbo: <http://dbpedia.org/ontology/> >> <http://dbpedia.org/ontology/>* >> *PREFIX dbr: <http://dbpedia.org/resource/> >> <http://dbpedia.org/resource/>* >> *SELECT ?city * >> *WHERE {* >> * ?city a dbo:City;* >> * dbo:populationTotal ?population;* >> * dbo:country dbr:France.* >> * FILTER (?population > 10000)* >> *}* >> >> *This query uses the dbo prefix to access the DBpedia ontology and the >> dbr prefix to access the DBpedia resources. It selects the names of cities >> (?city) that are instances of dbo:City, have a total population >> (?population) greater than 10000, and have the dbo:country property with >> the value dbr:France (which represents France).* >> >> We can see on social networks several tests of chatGPT related to >> ontologies. Do you think we can use chatGPT to query natural language >> ontologies (if we give it the structure before, of course)? And if we give >> a consequent corpus in learning to the GPT-3 algorithm (or its successor), >> do you think that it could build the ontology based on this corpus? More >> generally, will our vision of ontologies not be modified by the arrival and >> the rise of this kind of tool? >> >> Best regards, >> >> Xavier >> >
Received on Wednesday, 18 January 2023 14:28:19 UTC