Blog Post

[riedelcastro]

Regardless of whether the UAI submission comes through, I think we should publish the paper on arxiv at some point soon. For this I think it's extremely important to do a bit of PR. I have been thinking about a blog post that

1. gives a short overview and motivation for KBP
2. presents neural link predictors
3. presents our method
4. shows a simple 2D interactive animation that shows the adversarial learning process (and also the default learning process), using a simple model and problem. If we use a model like distmult, we should be able to relatively easily implement this in javascript. I have some ideas for this based on my talk slides.

We should be careful not to overdo this, and make sure this comes out with the paper. But I do think there is a "gap in the market" regarding nice neural link prediction articles and visualisations, and I think it's doable.

Is there a standard place where people put such posts (besides distill.pub)? We could just upload it to the uclmr webpage I guess.

[pminervini]

shows a simple 2D interactive animation that shows the adversarial learning process (and also the default learning process), using a simple model and problem. If we use a model like distmult, we should be able to relatively easily implement this in javascript. I have some ideas for this based on my talk slides.

Sounds great! I just need to start some experiments on adversarial regularisation for NLI this weekend, and I'll be on the post starting from Monday.

Could you please share your talk slides?

(Do you have any preference about the javascript libraries to use?)

[riedelcastro]

No preferences. I suppose there are at least two choices to be made:

• something for the visualisation (d3?)
• something to do the math (SGD)