Comments (5)
Yes, the configuration files should implement the same models reported in the paper.
I think you've answered your own question: the 4 layers for the sentence-level dilated CNN model are the 3 layers defined in the layers
json in dilated-cnn.conf
, plus the initial projection.
from dilated-cnn-ner.
Okay so does this mean, there is nowhere in the experiments where a dilation rate of 4 is used? Then does that affect the total receptive field of the CNN? since using a dilation of 2 doesn't give us a good level of receptive field(effective input width as per the paper).
from dilated-cnn-ner.
We experimented with models w/ dilation rate 4, but we found iterating smaller dilation widths to work better. This could partly have been an artifact of TensorFlow's old, naive (bad) implementation of dilated convolutions, which was very memory and time intensive, relative to what it should be. TF versions 1.5+ should have fixed this, so you may find that you can get better results with wider dilations / deeper networks, which should train faster and require less GPU memory now.
Our models still have a wide receptive field due to stacking w/ the dilation-2 layers, certainly much wider than the non-dilated equivalent number of layers.
from dilated-cnn-ner.
I am planning to make a pytorch equivalent of the research paper, and try few extensions for it. Thank You, for your quick replies. your quick replies would surely help me do it better and quicker.
from dilated-cnn-ner.
Great, let me know if you have further questions!
from dilated-cnn-ner.
Related Issues (20)
- Inference HOT 5
- What is the use of projection layer HOT 1
- Need some clarification on the settings HOT 2
- Training File HOT 1
- Training issue HOT 1
- Is the dilated cnn ner model stable? HOT 2
- Did you try your model on other seq labeling tasks like Chunking or POS? HOT 1
- Nan problem during training on ontonotes data set HOT 7
- Getting some issue with permission beyond my understanding HOT 3
- int() argument must be a string, a bytes-like object or a number, not 'map' HOT 2
- About the paper HOT 6
- details on the accuracy HOT 12
- preprocessing before triggering 'preprocess.sh' for ontonotes HOT 2
- Validate model on real text data HOT 4
- InvalidArgumentError: indices[11,21] = 243838 is not in [0, 243245)
- Inconsistent results when predicting a single sentence versus predicting labels for dev set HOT 4
- Support for Tensorflow 1.13 HOT 4
- Any pytorch version of dilated-cnn-ner around ? HOT 3
- Question for the paper (only)
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 dilated-cnn-ner.