Comments (6)
Yes, our ALBERT experiments are based on add_new_tokens
. Did you try just to use tokenizer.tokenize()
?
from pure.
Thanks for your reply!
I used tokenizer.tokenize() to find that the added_tokens.json did not work, it still only use the origin vocab.txt. What I really want is to keep the added token, rather than tokenized with wordPiece. Thus, I wondered whether re-pretraining is necessary so that I can use both origin and added tokens to apply the convert_tokens_to_ids() function in your experiment?
Could you please tell me the detailed steps of ALBERT experiments kindly, since I find the vocab_size was modified from 30000 to 30046 in rel-alb-ctx0.zip.
from pure.
Hi, I just want to check back and see whether you have resolved the issue.
I don't think you need to re-pretrain the model (we didn't in our ALBERT experiments). You may check this function to see how we augment the vocabulary.
from pure.
Hi, I also had this problem after trying to train a model with Bert base. Could you please answer me the following questions:
-
In the paper you also use base Bert to get the results of typed text markers. However, if I understand you correctly, Albert was used?
-
To add to that, in the code the "add_new_tokens" parameter is set to false per default and only to true for Albert. Why is that? If I understand the code correctly, only if this is set to true, the model will use the typed markers with entity labels and not the unknown token. Shouldn't this be true per default?
-
Can I just set the add_new_tokens parameter to true when I want to train base Bert (or any other model than albert) with it?
from pure.
@hero-png Thanks for your questions!
- We tried both BERT and ALBERT as the base model in our experiments with typed markers.
- For BERT experiments, we directly used the unused tokens in BERT vocabulary (
[unused1]
,[unused2]
) as the markers (check this line). For ALBERT experiments, we had to useadd_new_tokens
because there aren't pre-defined unused tokens in ALBERT vocabulary. - Yes, you can set
add_new_tokens
to be true when training BERT.
from pure.
@a3616001 Thank you very much for your quick reply!
from pure.
Related Issues (20)
- Missing predicted value HOT 1
- entity/models.py _get_input_tensors function HOT 2
- Multiple issues HOT 2
- different F1 with the same seed HOT 2
- tensorflow版本 HOT 1
- About the relation in datasets HOT 1
- [Paper] What are "gold" entity and relationship types? HOT 2
- Provide full environment
- Input Data Format HOT 5
- How to load models into Python HOT 2
- some code problems reguarding run_relation_approx(get_features_from_file) HOT 2
- where is the code of Efficient Batch Computations
- Approximation Model Training & Inference HOT 1
- entity is S or O ?
- Further question of f1 and e2e_f1
- 版本库问题 HOT 1
- 版本库问题
- ACE dataset
- Training a model on a dataset that is not ace04, ace05, or scierc HOT 1
- training model for WLP -- stuck in suboptimal solution
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 pure.