Presenting Doqume: AI-Powered Research Engine for Knowledge Workers
blog.doqume.com
blog.doqume.com
2. Do you do journal articles?
3. Do you have data on the biotechnology business? (I'm looking to start a biotech startup)
I'm re-tooling right now. Taking a break from computer stuff to do a Masters (maybe a PhD) in biology, which is in the middle of a long boom. Being better than everybody else at filtering large amounts of data (at a time when new techniques are being invented month by month and year by year) would be a really good investment.
1. First of all, thank you 2. Yes, we do. I'd first look at: (a) data set: Biotech is a broad area. We'd love to understand the specific use case. We have 50M entities in Doqume today, but we constantly work to integrate or build new sets. (b) work with the content resource: some journals are open, some not. If the abstract has enough information that's usually a good place to start. Otherwise we look at each journal and evaluate next steps. (c) build the engine. There can be very different needs there. I've covered some of it in the article, but let me know if you have any questions I'll be happy to tell you more. 3. Yes, we do.
Feel free to write me: vaidotas [at] doqume [dot] com. And congrats for your startup project!
Cheers, Vai.
I know this lessens the power of claiming they know stuff that is not available to the public, but I would think Wikidata has ways of establishing the provenance of the data, so they should get credit as well as the original Wikipedia authors.
We definitely plan to contribute information back to Wikidata and, in fact, we already did as part of our experiment. We contributed more than a thousand edits, mainly on company data like industry of operation. Of course, we need to strike a balance between what we contribute back and what we keep as competitive advantage.
Besides that, we always comply with licenses and give credit to the original source when this is required. For example, when displaying Wikipedia content there's always a prominent link to the page where the content has been extracted from.
We could use some moral support. Thanks for any feedback.
I'm from https://insideropinion.com
We built a very similar product (I think). We took a fundamentally different approach, but I'd be happy to share what did / didn't work for me. Take it for what it's worth though, I'm still bootstrapping myself.
My contact info should be discoverable from my profile.
We are using Entity Linking to detect entities in text. The algorithm takes into account context to disambiguate words, i.e., in "Mercury is a chemical element with the symbol Hg and atomic number 80" the word Mercury should be linked to the chemical element rather than the planet. When documents are indexed this way, the user is able to perform queries for specific concepts rather than simple keywords.
We had a demo open until a week ago, but we decided to close it to focus on finishing up some infrastructure work that will help us handle more efficiently maintenance of data sets. On the other hand we didn't want to drag it for too long and decided to just launch :)
We'll re-open to the public once we do that. If you're curious I can share a login for you to try it out.
We also have https://projectpiglet.com for investing.
If the Doqume team wants to chat, happy to!
I have a bit different approach in the way I structure the information, which is both limiting, but also useful to a set of problems.
Essentially, I built a content ranking system, which is a fair amount different than Google or your system. It's also patent pending, but I don't think necessary for what you're building at the moment.