Hacker News new | ask | show | jobs
by random_2azkXJ 4128 days ago
NLP researcher here.

From a simple test, this tool is at the hobby level. The text is not interpreted semantically, because the so-called summarization is nothing but blocks of text from the original text, copied ad-literam. It lacks any kind of rewording. My guess is that for content retrieval it employs the the most rudimentary model one can think of [1], does a plain token indexation, then chooses the blocks with the highest density of non-ordinary words.

[1] http://en.wikipedia.org/wiki/Standard_Boolean_model

1 comments

This is no hobby level system. I've done side-by-side comparisons and they've got something else going on here that beats other systems hands down. You've also seemed to miss the fact that these guys are enabling the context to be controlled using any word.