-
There is no trace about appendix A and appendix B of the Complex Embeddings for Simple Link Prediction
-
It seems that there is no norm for the embedding. So I wonder whether the performance can be as good as the paper's result
-
Dear THUNLP,
I installed OpenKE successfully but it reports segmentation fault when I run example.py.
> ~/OpenKE$ python example.py
> Input Files Path : ./data/FB15K/
> Output Files Path : …
-
There are a few things that still need to be done, that don't justify another paper, but would round things up and could be helpful in case of rejection.
What are these? For example, running on mor…
-
Hello Théo,
Thanks a lot for this piece of code, I've trying to understand the testing protocol from the code but unfortunately I couldn't.
I wonder what is the `positive to negative ratio` used…
-
Decide synthetic dataset, and which experiments to do on it.
-
Results on `DistMult` are not that enthusiastic (as e.g. in `TransE`). I am afraid this may be happening because the model tries to minimize the overall loss by increasing the magnitude of the predica…
-
Note - Experiments on FB15k can be a bit slow (take several hours); e.g. try this:
```bash
$ python3 ./bin/adv-cli.py --train data/fb15k/freebase_mtr100_mte100-train.txt --valid data/fb15k/freebas…
-
my configuration is:
ubuntu 16.04
python 3.5.2
GCC 5.4.0
tensorflow 1.1.0
the output of make test is the following
```
pytest tests -v -m "not (smalldata)"
==================================…