Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Can you articulate why this is different to other text summarising solutions?

It may be that yours is easier to integrate than using AWS APIs[1], or performs better than what's available on say, npm[2]. It may be that your algorithm is designed specifically for news articles.

If you can articulate where this fits into the market of other solutions - that will help inform how best to utilize it.

[1] https://aws.amazon.com/blogs/machine-learning/part-1-set-up-...

[2] https://www.npmjs.com/package/text-summary



Word 2007 had an "AutoSummarize" feature which was later removed.[1] I wonder how well it would hold up today.

[1] https://youtu.be/o30nPCgdq0I?t=100


Why is it different? Hard to tell, I don't know how others work. I was focusing strictly on news articles


If it's hard to tell the difference, it'll be hard to sell the difference. (Cheesy rhyme intentional)

But seriously, you could probably do some research to work out your solution's strengths, relative to existing solutions.

When you know what it's strengths are, try to find people who want those strengths.

Ultimately, you're asking the question 'is there a market for what I've built?' - but you've phrased that question differently.


> If it's hard to tell the difference, it'll be hard to sell the difference

That's going into my quotes list. Rhymes, is short and gets an important point accross. Bravo.


I’m not sure how relevant it is. Dropbox entered into a market with around 10 competitors, and trounced them all. In general it’s a mistake to worry about the competition.


Comparisons to competition are just a way to map out the market, and where you may fit.


Everyone else is focusing on news articles as well, so that's not a problem; however without comparison to other approaches it's impossible to tell if the solution is 'powerful' or even any good at all.

This here - http://nlpprogress.com/english/summarization.html - would be an overview of what algorithms are currently considered 'good' and what results they achieve on some datasets commonly used for evaluation and comparison, it would be interesting to run your solution on that data and see what you get.


Wow awesome, I'll try that




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: