h10
AI
text summarization
SHOW HN2017
How HN took it
2 positive, 16 neutral or asking, 0 mixed, 4 critical, out of 22 comments about the project. Thread score -0.07.
Execution: 0 for, 3 againstIdea: 2 for, 0 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
Useful idea for skimming HN articles
From 2 comments
The summary seems to pick the most unique sentences, so maybe LexRank? Amazing though, I've been really wanting a way to skim HN articles quicker, since there is so much volume…
mendeza on HNI'm glad that someone made this! Ever since I've known about ML and HN I've wanted to make something like this
spraak on HN
Objections
Summary method unclear and needs explanation
From 2 comments
This would really benifit from an explanation of what I'm seeing. can't really upvote it without knowing what's going on....
alistproducer2 on HNCan you describe a little about how you go from raw text to a summary? Is this supervised learning? If so, what is the training data?
ostegm on HN
Some posts missing comment links
From 1 comment
There are still posts with no link to the comments. Seems like it is happening whenever the summary is also missing below the title (currently "5. Ask HN: Leave job right before…
alexilliamson on HN
Web page throws a JS error on load
From 1 comment
js error: "get top stories error index.html:56:4"
singularity2001 on HN
Requests
Publish the source code
From 3 comments
This. It would be great if we can have the source code alongside with OP's comment on his/her summarization
a_c on HNAgree. It would be great to see your source code if at all possible, would be greatly appreciated.
apapli on HNIs this open source?
mulrian on HN
Link to HN comments for each post
From 1 comment
It would be good if it still included a link to the HN comments for each post
s_ngularity on HN
Questions
Which summarization algorithm is used
From 2 comments
Got that this is using nltk. Can you comment on which summarization algorithm you are using (TextRank, SumBasic and etc.) What's the motivation towards choosing one algorithm…
xiamx on HNWhat summarization algorithm are you using?
brunopedro on HN
Is there machine learning or training data involved
From 2 comments
Can you describe a little about how you go from raw text to a summary? Is this supervised learning? If so, what is the training data?
ostegm on HNNLTK has no machine learning algorithm AFAIK
amirouche on HN
Alternatives named
newspaper library for text extraction
From 1 comment
Not sure what do you use to scrape, but I can recommend newspaper to extract text. I contributed a while ago and it was pretty solid. https://github.com/codelucas/newspaper
ecesena on HN
Mercury web parser API
From 1 comment
You could probably get cleaner input for step 1 via the Mercury API [https://mercury.postlight.com/web-parser/] — it has a lot of affordances for different kinds of HTML…
jeffehobbs on HN
thepul.se news summarizer
From 1 comment
https://thepul.se/ also uses an algorithm based on nltk to summarize general news. (It also includes a nice speed-reader.)
travelinreid on HN