TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

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

71 pointsby christophe971over 11 years ago

9 comments

nnxover 11 years ago
It&#x27;s a very MVP simple implementation that works well for most cases. Kudos.<p>That said, looking at the code, I&#x27;m not sure why you call it an AI when it is very rule-based so the code itself is not able to have any &quot;intelligent&quot; behavior when the input falls out of the predefined rules.<p>More importantly, as you seem to be the creator of the underlying BigDb project, is there any actual data in it past the precise examples given in your README?<p><a href="http://thebigdb.com/recent" rel="nofollow">http:&#x2F;&#x2F;thebigdb.com&#x2F;recent</a> The only recent examples visible are about the weight and dimensions of the iPhone 5 vs Galaxy S4 vs Nexus 5, as in your NLP examples.<p><a href="http://thebigdb.com/random" rel="nofollow">http:&#x2F;&#x2F;thebigdb.com&#x2F;random</a> Gives the same results, I expect random takes the whole DB as the sample set.<p><a href="http://thebigdb.com/search?q=everest" rel="nofollow">http:&#x2F;&#x2F;thebigdb.com&#x2F;search?q=everest</a> No result found.
评论 #7090514 未加载
sinkasapaover 11 years ago
I think it is strange how the author of a cool tool like this seems to feel the need to justify their tool&#x27;s existence in a world where new web-framework X is announced every day.
评论 #7091318 未加载
TeeWEEover 11 years ago
Why don&#x27;t you use an existing ontology&#x2F;knowledge graph instead of building your own with thebigdb?<p>For example: <a href="http://www.freebase.com/" rel="nofollow">http:&#x2F;&#x2F;www.freebase.com&#x2F;</a>
评论 #7090767 未加载
pmelendezover 11 years ago
I like the idea, but unfortunately I only got results with the example questions. For instance:<p>&gt; akiva ask &quot;What&#x27;s the weight of an iPhone 5s ?&quot; 112 grams<p>is fine, but:<p>&gt; akiva ask &quot;What&#x27;s the weight of an iPhone 5 ?&quot; Sorry, Akiva can&#x27;t answer that question for now.<p>Or &gt; akiva ask &quot;What&#x27;s the weight of a Nokia Lumia 920 ?&quot; Sorry, Akiva can&#x27;t answer that question for now.
评论 #7090821 未加载
aluhutover 11 years ago
I wish there would be a cleaner V2 version of megahal out there. I loved that thing but the last time I&#x27;ve implemented it into eggdrop (which is hopelessly outdated too) I was sweating blood and never wanted to touch it again ;)
oelmekkiover 11 years ago
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 ?
评论 #7090359 未加载
silentrobover 11 years ago
This looks amazing, and I agree, you need to bootstrap theBigDB with more facts. Sources like freebase and perhaps DBPedia would help.<p>It would also be cool to layer on temporal facts too, like &quot;What is the price of APPL today?&quot; or &quot;Is JT on tour?&quot;<p>My initial statement was &quot;Is Kevin Spacey in Austin Powers?&quot; - No results.
tylerkahnover 11 years ago
As 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.
casualobsover 11 years ago
this is interesting, but none of the questions i&#x27;ve asked seem to get answered, even after wording them well and picking easy questions..like 20 questions in a row