DBpedia Live Neural Question Answering Chatbot - GSoC2020

@emarx Do we have to develop a telegram bot or a bot server which it can be configurable to connect with any messenger service or if need configurable on website it self?

@emarx How can we discuss ideas with the mentors? Is there any group mailing list or we can just mail the mentors directly? Or there is any other preferred medium?

Dear Randikaj,

Thanks for your question.
The intend of using Telegram in the warmup task was only to get you familiar with the project.
As I mentioned previously, you are free to suggest architecture and integration with other systems.
However, the main focus here is DBpedia using the DBNQA and NSPM projects.

1 Like

Dear harshit-gupta,

You and any student that want to discuss some aspects of her/his proposal can mail me directly.
Please be aware that answering all emails can take some time.
You can find my contacts on the AKSW website: http://aksw.org

1 Like

@emarx Thank you so much. I started to work on the proposal. I would like to know how can I share the proposal with you for getting feedback?
I saw that the telegram bot supports spraql queries too other than the natural language queries. Should the new bot also needs to support spraql queries ?

Dear Randikaj,

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.

1 Like


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.


Kartavya Kothari

Dear Kothari,

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. :wink:

@emarx Will it be okay to use Rasa NLU for the project?

Dear @randikaj,

No you can’t.
The idea is to build our own Rasa using NSPM and DBNQA.
You can try to answer to this question on your proposal.


1 Like

@emarx Thank you so much, I have doubt on that. I will share my initial design with you

@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?

Dear @randikaj,

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. :wink:

1 Like

@emarx What do you mean by using DBPedia? It means use DBPedia existing models to build the intent classification model and context management model?

Dear @randikaj,

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.


1 Like

@emarx Thank you, Now I know the scope of the project :grinning:

*To everybody, @kartavyakothari @randikaj @grimmerygonsa @tantrojan @harshit-gupta

We started to collect the proposal drafts to have an estimation of project slots.
Please submit ASAP your drafts via GSOC website.

1 Like

Sure, I will update my draft proposal in GSoC site ASAP

@emarxThanks for your review for my early design. I have started to write the proposal on a new document. I will update it in the GSoC site.

Good information thanks for sharing