ann-writer
AI
text generation
SHOW HN2015
How HN took it
2 positive, 3 neutral or asking, 1 mixed, 13 critical, out of 19 comments about the project. Thread score -0.31.
Execution: 0 for, 7 againstPerformance: 0 for, 3 againstIdea: 1 for, 2 againstDocs: 0 for, 1 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
Fun hack and good idea for matching house writing style
From 3 comments
Fun hack. If anything, it highlights how compelling deep learning and RNNs are: no messing with NLP, no messing with building other features or adding up classifiers, etc. The…
frisco on HNI'd be interested to know if this could be turned into a tool that lets you know how well your writing (or coding) matches the "house style". (Mostly for technical documentation,…
w_t_payne on HNThis is brilliant! I tried it out. Waiting for a larger data set! +1
scorpwarp23 on HN
Objections
Not a real neural network; it uses k-nearest neighbors classifiers
From 3 comments
this doesn't look like a neural net to me. from NeuralNetwork.py ``` from sklearn.neighbors import KNeighborsClassifier # Create a sperate neural network for each identifier for…
strong_ai on HNSo then it seems like the author of the code doesn't understand that "NN" means "Nearest Neighbors" and not "Neural Network"? He mentions that he used sklearn's Neural Network…
ching_wow_ka on HN> I decided to use scikit's machine learning libraries. [...] The writer I create uses multiple SVM engines. One large neural network for the sentence structuring and multiple…
achompas on HN
Output quality is no better than a Markov chain
From 3 comments
I haven't looked at the code, but glancing at the results leaves me thinking it might need more work. The output seems to me around the level a Markov chain might produce.…
nl on HNI ran a Markov chain text generator on Finnegans Wake once. It came out looking much the same. :-)
Turing_Machine on HNFun hack. If anything, it highlights how compelling deep learning and RNNs are: no messing with NLP, no messing with building other features or adding up classifiers, etc. The…
frisco on HN
Copyright concerns over using Harry Potter text
From 2 comments
Have you considered the copyright on the Harry Potter training data?
caf on HNI would still be cautious. There is no need to use exactly this text. Anyway, there are countries that don't have a fair use policy. So in this countries your repository could…
bhaak on HN
Requests
Larger training dataset
From 1 comment
This is brilliant! I tried it out. Waiting for a larger data set! +1
scorpwarp23 on HN
Tool to measure how closely writing matches a house style, possibly as a Sublime Text plugin
From 1 comment
I'd be interested to know if this could be turned into a tool that lets you know how well your writing (or coding) matches the "house style". (Mostly for technical documentation,…
w_t_payne on HN
Questions
Whether the normalization procedure was sound
From 1 comment
I am afraid this author has no idea what he is doing - and is loosely throwing around terms he does not understand. What the hell was his normalization procedure. Dangerous to…
bearzoo on HN
Alternatives named
Karpathy's char-rnn
From 2 comments
I haven't looked at the code, but glancing at the results leaves me thinking it might need more work. The output seems to me around the level a Markov chain might produce.…
nl on HNFun hack. If anything, it highlights how compelling deep learning and RNNs are: no messing with NLP, no messing with building other features or adding up classifiers, etc. The…
frisco on HN
Markov chain text generators
From 2 comments
I ran a Markov chain text generator on Finnegans Wake once. It came out looking much the same. :-)
Turing_Machine on HNI just can't agree that a simple, linear-time operation like "tokenizing words and basic n-gram models out of them" is a tedious problem like you seem to be implying, nor do I…
kylebgorman on HN