Can't run tutorial_parser.ipynb on GPU

When I pasted all the contents into a single Python file and run the following:
```
python parser.py --dynet-gpus 1 --dynet-mem 10000
```
It throws the following Not Implemented error:
```
[dynet] initializing CUDA
Request for 1 GPU ...
[dynet] Device Number: 0
[dynet] Device name: Tesla K80
[dynet] Memory Clock Rate (KHz): 2505000
[dynet] Memory Bus Width (bits): 384
[dynet] Peak Memory Bandwidth (GB/s): 240.48
[dynet] Memory Free (GB): 11.927/11.9956
[dynet]
[dynet] Device(s) selected: 0
[dynet] random seed: 3589591803
[dynet] allocating memory: 10000MB
[dynet] memory allocation done.
Traceback (most recent call last):
File "parser.py", line 206, in
dev_loss += loss.scalar_value()
File "_gdynet.pyx", line 947, in _gdynet.Expression.scalar_value (_gdynet.cpp:23604)
cpdef scalar_value(self, recalculate=False):
File "_gdynet.pyx", line 960, in _gdynet.Expression.scalar_value (_gdynet.cpp:23509)
return c_as_scalar(self.cgp().get_value(self.vindex))
RuntimeError: RestrictedLogSoftmax not yet implemented for CUDA (contributions welcome!)
```

Does that mean this notebook can only run on CPU for now?

Start by reproducing the command from parser.py and compare its behavior with tutorial_parser.ipynb on CPU and GPU. Investigate the reported DyNet RestrictedLogSoftmax CUDA error; done should establish whether the tutorial supports GPU execution or identify the documented limitation.

Scritto dal modello di indicizzazione a partire dal testo della issue.