-
http://tech-blog.abeja.asia/entry/poincare-embeddings
-
In the supervised settings we can also try the poincare embeddings as features. The idea is that compositional phrase, e.g. 'green forest' has the same hypernym as 'forest' while 'hot dog' and 'dog' h…
-
## 一言でいうと
階層構造をもつ自然言語情報を、階層情報の表現に適した双曲空間に埋め込むという研究。200次元の分散表現を5次元にまで圧縮できる。
### 論文リ…
-
Hi,
Thanks a lot for open-sourcing both this and the original poincare embeddings paper.
The authors of the original paper (poincare embeddings) have [another](https://arxiv.org/pdf/1806.03417.pdf…
-
Hi @alex-tifrea ,
I'm training word embeddings on the [RCV1 corpus](http://www.ai.mit.edu/projects/jmlr/papers/volume5/lewis04a/lyrl2004_rcv1v2_README.htm). I've generated the vocab (7MB) and co-oc…
-
Hi! I was wondering which classes/functions should be used to map, for example, a BERT embedding to the hyperbolic space (using the Poincaré ball model). In the paper it is mentioned that you use an …
-
I'm trying to reproduce the figure in the README or figure 4 of the paper, and I am doing the default settings of the poincare-embeddings for producing wordnet embeddings. Are there any particular par…
-
I am getting the following error after following the installation instructions. Could you please advice how to resolve it?
`(poincare) local-poincare-embeddings $./train-mammals.sh
Traceback (mos…
-
The current implementation makes use of [autograd](https://github.com/HIPS/autograd/) to auto-differentiate the loss function. As the automatic differentiation is too slow, we chose to not use this fe…
-
Hi there,
I have a quite large dataset and GPU usage that does not exceed 24 hours. In this case, I need to restore from checkpoint and continue to train the old models.
The current situation is tha…
lkcao updated
5 months ago