Show HN: Akiva – A simple NLP, question-answering artificial intelligence

Re:Show HN: Akiva – A simple NLP, question-answering artific... by TeeWEE on Monday January 20, 2014 @12:46PM (#7090733)

Why don't you use an existing ontology/knowledge graph instead of building your own with thebigdb?

For example: http://www.freebase.com/

[ Parent | on HN ]

Re:Show HN: Akiva – A simple NLP, question-answering artific... by christophe971 on Monday January 20, 2014 @12:51PM (#7090767)

Because I believe the knowledge graph of Freebase is way heavier than what's needed, and unless you know exactly the type of what you're looking for, it would make a software like Akiva way more complicated to build, imho. (or I missed something)

[ Parent | on HN ]

Re:Show HN: Akiva – A simple NLP, question-answering artific... by hcarvalhoalves on Monday January 20, 2014 @03:14PM (#7091516)

Your project sounds awesome, the NLP part seems to be working nicely, but I'm afraid it depends on the quality of the data source, which right now is empty (I only saw some facts about a few smartphones). I remember your announcement for TheBigDB [1], and thought it had some fundamental structural limitations as a fact database too.

Since ontology is a very very hard problem, and collecting a lot of facts even more so, I think you should look more carefully into using a structured DB like Freebase that has already figured it out.

[1] https://news.ycombinator.com/item?id=5493042

[ Parent | on HN ]