Viewing profile — jgehring

There's not that much Uranium actually that's economically sensible to extract. The NEA says in their 2024 report on Uranium [1]: > Considering both the low and high nuclear capaci…

That's what happens in the very last layer. But at that point the embedding for "was" got enriched multiple times, i.e., in each attention pass, with information from the whole con…

"I don't care about cookies"?

Indeed. For bad news, e.g. crime, the (German) media takes great care to mention whether suspects or convicts are immigrants or of direct immigrant descent. Attaching this informat…

I think your parent paints a rather extreme picture. The two examples they picked, Wiehre and Herdern, are the upscale neighborhoods with plenty of mansions, and there's rather onl…

> If you don't, then like in many south-German cities (located in mountain valleys where space is scarce), you're living in a place without any green in sight While this is general…

Nice to see my neighborhood (Vauban) featured here :) It's an awesome place to raise kids as it provides an almost village-like environment, being right at the edge of the city and…

Agree, it's so convenient for grabbing fields that I ended up writing a bash script that generates an awk script since the '{print $1}' is cumbersome to type, and I can never remem…

You're right, these issues can also be tackled independently. Transfer learning can help, but my first guess would be that it's hard to get reasonable accuracy (= usable for applic…

When training speech recognition systems you want to use data that closely matches your target domain. Models trained on audiobooks read by professionals will not perform very well…

Yes! The API feels very much like using PyTorch from Python, and implementing models and working with tensors purely in C++ is very convenient. We're using it for our research plat…

Yes, ByteNet v2 outperforms LSTMs on characters but not on word pieces. It would be interesting to see how our model performs on characters, especially when scaled up to the size o…

There is no online demo but you can run the pre-trained models on your local machine: https://github.com/facebookresearch/fairseq#quick-start . CPU-only versions of the models are …

Yes, there have been a couple of attempts to use CNNs for translation already, but none of them outperformed big and well-tuned LSTM systems. We propose an architecture that is fas…

Yes, that's pretty accurate. Step 3 (attention) is repeated multiple times, i.e. for each layer in the decoder. With each additional layer, you incorporate more of the previously t…