Comments (4)
This kind of issues with fastBPE typically happens when you have too many BPE codes and a too small vocabulary.
What is your vocabulary size, and how many BPE codes are you trying to compute?
from unsupervisedmt.
Ok, I get it.
can you suggest how many code should i compute for dataset has 610 sentence in each file (train, test, valid). it is also not extract correct vocabulary. its only extract alphabets instead of words. as shown in image. it is computing just 93 vocabulary size.
for 610 sentences, I have tried different values in almost 200 to 1500 for BPE code. for each code value it is giving same issue.
Although dataset is very small, but at this time my task is to run this technique successfully. Next I will increase dataset.
from unsupervisedmt.
610 sentences is very small. I would simply use word level and not BPE in this case.
BPE is useful to reduce the vocabulary size and to avoid computing a softmax over hundred of thousands of elements. But in your case the vocabulary will be very small so you probably don't need BPE.
from unsupervisedmt.
ok, thanks for replying. can you guide me little bit more. which part of data.enfr.sh I should remove, what to insert in the code to this.
from unsupervisedmt.
Related Issues (20)
- why MemoryError
- for different language, where to make change?
- How to train NMT + PBSMT ?
- UnboundLocalError: local variable 'n_words' referenced before assignment
- About number of shared layers
- RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [14, 32, 1536]], which is output 0 of AddBackward0, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True). HOT 1
- How to run PBSMT +NMT ?
- transformer multihead attention scaling layer error
- Setting the random seed does not result in same outputs across runs
- I have trouble when run get_data_enfr.sh
- How can I modify the code to train may own dataset on specific language?
- Low utilization rate of cuda HOT 1
- How to train the vector of phrases
- Low BLEU on PBSMT HOT 3
- bpe_end issue
- Getting raise EOFError() while executing Linux Command through Netmiko
- How i can run MUSE alignment in .sh
- How to train the model without para_dataset
- Error in runny bash command. HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from unsupervisedmt.