[paubric]

What it says on the tin: BERT attention per token gets converted to CSS styling to grab the user's attention. The idea came from thinking about content consumption as perceiving large bodies of information, rather than searching for a specific document. In this framing, attention becomes a building block of a "perceptual engine," which itself has a few nice-to-haves: abstraction, top-down influences, interactivity. More details in the write-up/demo, I'll stick around to answer questions.

[jcun4128]

I don't know what BERT is briefly looked it up. I also looked at the site the pulsing varying color intensity targeting certain words.

Is this like a summarizer or no? I have been passively looking into ways to scan threads like in HN on popular articles and a visual tool like this could be neat via Chrome Extension.

It just seems like people's summaries are different. Although I suppose standardized tests wouldn't work if there wasn't some consensus on the point of a paragraph.

[paubric]

Thanks for the interest! What I've been playing with in the project is not really a summarizer, though I think it could work well with a summarization model. This one is simply about highlighting relevant bits of a certain text (be it the original or a summary), so that you can then "scan" it in interesting ways.

I totally agree that people's summaries of the same original article are different, and moreover that the best summary for you personally is different from mine, and different from anyone else's. It should not tell you what you already know, for instance. But again, whole different can of worms..