Comments (2)
Hello,
I know that in the gnmt encoder only the first layer is bidirectional.
That is the difference.
Is it possible that a 2-layer gnmt encoder could give better translations than when a 2-layer brnn encoder is used?
It depends on the dataset and optimizer. However, BRNN has more parameters than GNMT for the same number of layers so it should perform better when the training data is large.
from opennmt.
Understood! Thanks a lot.
from opennmt.
Related Issues (20)
- Decoder.lua:446: 'for' limit must be a number HOT 1
- Error when translating with Language Model: "attempt to call method 'forwardOne' (a nil value)" HOT 2
- Meet with lua:446:'for' limit must be a number HOT 2
- Difference between using epoch and train_steps HOT 3
- WriteObject problem, bad argument #1 to 'ipairs' HOT 1
- IDEA: Process FOSS projects .po files for translation corpora
- The engine caches the data in the translation HOT 6
- How to speed up when preprocess the corpus ? HOT 1
- Embeddings: invalid line count HOT 3
- Test BLEU Score HOT 1
- share_embedding option HOT 2
- Better pre-trained PyTorch models
- Maximum length of string processed by the engine HOT 2
- unicode issue for translating Bangla to English HOT 2
- Error BPE tokenizer: tokenize.lua:87: attempt to concatenate upvalue 'line' HOT 3
- Is early stopping available in OpenNMT-py or OpenNMT-tf? HOT 1
- Is `early-stopping` available feature in OpenNMT-tf or OpenNMT-py?
- NMT, What if we do not pass input for decoder? HOT 1
- ModuleNotFoundError: No module named 'onmt.inputters' HOT 1
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 opennmt.