News for hackers. Stuff that matters.
Re:Show HN: NLP-based tool for technology research by xtiansimon on Monday April 13, 2020 @10:16AM (#22856010)
I've toyed with scripts from my NLP research, but nothing to this extent. Kudos.

The webpage looks clean. The ratios of graphic elements to their scale is pleasant. The two-tone color palette is pleasant. The line length in the main screen (~140 c/l) is a bit much for my taste.

As far as the Try now, I'm not sure how these relate to each other. Maybe a video demo walk-through taking one technology, such as the digital watch (which we are all familiar) and walking it through the site?

As a "Try now" user, until I can throw in any random data and see it propagate through your product, I won't realize what you've accomplished.

Re:Show HN: NLP-based tool for technology research by BLP4YC on Monday April 13, 2020 @10:44AM (#22856269)
Thanks! I have been experimenting with NLP for two/three years now and this finally something somewhat useful. So your comment makes me really happay!

Thanks for your feedback regarding the main page. I also like the design, but not because I made, but because the developers behind the templates did such a great job: https://startbootstrap.com/themes/sb-admin-2/ + https://blackrockdigital.github.io/startbootstrap-landing-pa...

I probably should give them credit more prominently (right now, I do it only in the source code).

Regarding the "try now": I have never thought that this will be an issue. On the contrary, I thought that different data across different features will enable people to better understand the variety of the product. But what you are saying makes absolute sense. I have added your points to my todo.

Again, thanks a lot for your feedback - it really helped.

Re:Show HN: NLP-based tool for technology research by Endlessly on Monday April 13, 2020 @01:30PM (#22857902)
Agree with the feedback on being able to take a raw inputs such as even a manually selected set of documents such as wiki-pages, patents, research papers, etc — and see both the high-level workflow and even step-by-step the transformations and related code.

Clearly, that’s asking a lot both in terms, work and IP disclosure, but I am guessing what the average user would want, that is they have a specific need based on existing documents that the want ingested for analysis. Maybe I am wrong, but agree when doing a quick look, aside from the raw data & code, what I thought to look for to try and understand what was really there.