Akiva
AI
question answering
SHOW HN2014
71points
20comments
#427of 2,272 in 2014
Top 19%of 2014 by points
How HN took it
MixedNo clear lean
2 positive, 4 neutral or asking, 3 mixed, 3 critical, out of 12 comments about the project. Thread score -0.04.
Performance: 0 for, 3 againstIdea: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Works well for the example questions and is a nice MVP
From 2 comments
It's a very MVP simple implementation that works well for most cases. Kudos. That said, looking at the code, I'm not sure why you call it an AI when it is very rule-based so the…
nnx on HNI like the idea, but unfortunately I only got results with the example questions. For instance: > akiva ask "What's the weight of an iPhone 5s ?" 112 grams is fine, but: > akiva…
pmelendez on HN
Objections
Database is nearly empty, so most questions go unanswered
From 5 comments
It's a very MVP simple implementation that works well for most cases. Kudos. That said, looking at the code, I'm not sure why you call it an AI when it is very rule-based so the…
nnx on HNI like the idea, but unfortunately I only got results with the example questions. For instance: > akiva ask "What's the weight of an iPhone 5s ?" 112 grams is fine, but: > akiva…
pmelendez on HNSame here... I tried really different kinds of questions and couldn't get an answer. ``` $ akiva ask "Is the empire states building higher than the eiffel tower ?" Sorry, Akiva…
bromagosa on HNthis is interesting, but none of the questions i've asked seem to get answered, even after wording them well and picking easy questions..like 20 questions in a row
casualobs on HNThis looks amazing, and I agree, you need to bootstrap theBigDB with more facts. Sources like freebase and perhaps DBPedia would help. It would also be cool to layer on temporal…
silentrob on HN
Called AI but it is rule-based
From 2 comments
It's a very MVP simple implementation that works well for most cases. Kudos. That said, looking at the code, I'm not sure why you call it an AI when it is very rule-based so the…
nnx on HNAs best I can tell this is more like an English-looking CFG with a simple attribute grammar. And the rules can be updated at runtime.
tylerkahn on HN
Should use an existing knowledge base like Freebase instead of TheBigDB
From 2 comments
Why don't you use an existing ontology/knowledge graph instead of building your own with thebigdb? For example: http://www.freebase.com/
TeeWEE on HNYour 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…
hcarvalhoalves on HN
Requests
Populate TheBigDB from Freebase or DBpedia
From 3 comments
have you considered integrating with freebase or perhaps populating theBigDB from freebase? http://www.freebase.com/
kybernetikos on HNThis looks amazing, and I agree, you need to bootstrap theBigDB with more facts. Sources like freebase and perhaps DBPedia would help. It would also be cool to layer on temporal…
silentrob on HNYour 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…
hcarvalhoalves on HN
Add speech recognition
From 1 comment
Very nice. I wonder, do you plan to couple this with any kind of speech recognition at any point, so we could have some kind of custom siri ?
oelmekki on HN
Questions
Why call it AI when it is rule-based
From 1 comment
It's a very MVP simple implementation that works well for most cases. Kudos. That said, looking at the code, I'm not sure why you call it an AI when it is very rule-based so the…
nnx on HN
Why not use an existing ontology like Freebase
From 1 comment
Why don't you use an existing ontology/knowledge graph instead of building your own with thebigdb? For example: http://www.freebase.com/
TeeWEE on HN
Alternatives named
Freebase
From 2 comments
have you considered integrating with freebase or perhaps populating theBigDB from freebase? http://www.freebase.com/
kybernetikos on HNWhy don't you use an existing ontology/knowledge graph instead of building your own with thebigdb? For example: http://www.freebase.com/
TeeWEE on HN
DBpedia
From 1 comment
This looks amazing, and I agree, you need to bootstrap theBigDB with more facts. Sources like freebase and perhaps DBPedia would help. It would also be cool to layer on temporal…
silentrob on HN
MegaHAL
From 1 comment
I wish there would be a cleaner V2 version of megahal out there. I loved that thing but the last time I've implemented it into eggdrop (which is hopelessly outdated too) I was…
aluhut on HN