Under the scope of DBNQA, the chatbot will basically be translating natural language queries to SPARQL.
However, yes, you can suggest new ways of interacting with DBpedia’s content through natural language queries.
As I’ve mentioned earlier you can send me your proposal for a quick look before submission, but that does not guarantee your selection.
I will not give any advice on ideas, but rather check the structure.
Regardless of your selection in the GOC2020, all students are always invited to collaborate.
I am Kartavya kothari, a computer science mtech student at IIT bombay. I am working in the field of information retrieval under Proff Soumen chakrabarti (soumen@cse.iitb.ac.in). This is one of the topics I am interested in under DBpedia. I am haflway done with the warmup tasks so just wanted to introduce myself.
I wanted to know how crazy can we go on the proposed project. I have gone through some recent papers on conversational QA which I think can be implemented with the chatbot client.
You are free to suggest enhancements.
However, the main focus here is DBpedia using the DBNQA and NSPM projects.
Try to be conscious regarding the short time that you have to deliver your ideas.
@emarx since NSPM model only performs the machine translations from natural language queries to SPARQL queries, in order to give the chatbot an ability to maintain natural conversation with user I believe it requires models to perform intent classification and context management. Since we are not allowed to use existing models like Rasa, shall I build my own models or the project is sctrick only to use the NSPM model?
The short answer is your own. You need to discuss how to do it using DBpedia. Perhaps, in this case, building your own intent classification and context management models. We do not want to use third-party software/models.
That’s exactly the fun part.
You can propose an intent classification and context management modules for the Chatbot. Just be aware that it will be used for accessing DBpedia content.