54.86.121.4

AI

text summarization

SHOW HN2016

126points
56comments
#285of 2,264 in 2016
Top 13%of 2016 by points

How HN took it

RoastedHalf or more of the comments are critical

1 positive, 12 neutral or asking, 2 mixed, 15 critical, out of 30 comments about the project. Thread score -0.40.

Execution: 0 for, 12 againstIdea: 1 for, 2 againstDesign: 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

  • Good quality summaries on some articles, especially BBC news

    From 2 comments
    • Good quality summaries, but it seems it caches pages based on their base URL, and throws away the query parameters. Some blogs use query parameters to distinguish between…
      microcolonel on HN
    • I'm not sure I am seeking the same wow-factor results from the service that everyone else is raving about. I submitted this link [0] which was on the HN homepage a couple of days…
      ComputerGuru on HN

Objections

  • Results are often poor, picking unimportant or misleading sentences

    From 3 comments
    • I'm not sure I am seeking the same wow-factor results from the service that everyone else is raving about. I submitted this link [0] which was on the HN homepage a couple of days…
      ComputerGuru on HN
    • Huum, not quiet sure what is was expecting, but the results were not great :( But I could see the use of this kind of service. Also does not work with accentuated char.
      h1fra on HN
    • Not really working as expected :(
      orliesaurus on HN
  • Fails on some sites such as WordPress blogs and non-English or accented text

    From 2 comments
    • Wordpress sites urls are not working !!
      gkumartvm on HN
    • Huum, not quiet sure what is was expecting, but the results were not great :( But I could see the use of this kind of service. Also does not work with accentuated char.
      h1fra on HN
  • Query parameters are dropped, so distinct articles may be cached together

    From 1 comment
    • Good quality summaries, but it seems it caches pages based on their base URL, and throws away the query parameters. Some blogs use query parameters to distinguish between…
      microcolonel on HN
  • Not really a summary, only sentence extraction

    From 1 comment
    • Not summary, just sentence ranking and extraction. Still cool but not anything new. Sweet side project though! For anyone wondering how this was done, I have a similar project up…
      peter_l_downs on HN

Requests

  • Explain how it works and what it is built with

    From 3 comments
    • I'd like more details. How does it work?
      an_ko on HN
    • What is it built with? (Stack, Foss etc)
      LinkPlug on HN
    • Any details about the backend/implementation? shameless plugs for two similar projects(open sourced both) I did a while back 1) Algorithmic Summarizer:…
      mohaps on HN
  • Return JSON as an array rather than indexed keys

    From 1 comment
    • An array would be a better choice of structure for the sentences instead of hard coding the indexes.."1"...
      _RPM on HN
  • Use a domain name rather than a bare IP address

    From 1 comment
    • Good luck with the link still being usable in a month or a year. There's a reason we use domain names for sharing. Not only because they are friendly to read and remember, but…
      developer2 on HN

Questions

  • What are the alternatives to this?

    From 1 comment

Alternatives named

  • Textteaser

    From 1 comment
  • thegist

    From 1 comment
    • http://thegi.st It's a bit buggy still. To get a sense of it, stick to BBC articles.
      stkbach on HN
  • Algorithmia

    From 1 comment
    • Check out https://algorithmia.com/. Stuff like this plus a bunch more. Real business model so you can have more confidence in it.
      jbeda on HN
  • bookshrink

    From 1 comment
    • Not summary, just sentence ranking and extraction. Still cool but not anything new. Sweet side project though! For anyone wondering how this was done, I have a similar project up…
      peter_l_downs on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/11191394)