Comments (2)
For this dataset, we use the following setting (the summarization option is off). We used roberta, the drop_col da operator, the general dk, and a batch size of 32 for this dataset. The command should look like this:
CUDA_VISIBLE_DEVICES=0 python train_ditto.py \
--task Structured/Beer \
--batch_size 32 \
--max_len 256 \
--lr 3e-5 \
--n_epochs 40 \
--finetuning \
--lm roberta \
--fp16 \
--da drop_col \
--dk general`
I just re-ran the experiment and here are the results:
Baseline (no dk or da)
=========eval at epoch=40=========
Validation:
=============Structured/Beer==================
accuracy=0.967
precision=0.867
recall=0.929
f1=0.897
======================================
Test:
=============Structured/Beer==================
accuracy=0.967
precision=0.824
recall=1.000
f1=0.903
======================================
With DK (general) only
Somehow the test result is the same as the baseline.
=========eval at epoch=40=========
Validation:
=============Structured/Beer==================
accuracy=0.967
precision=0.824
recall=1.000
f1=0.903
======================================
Test:
=============Structured/Beer==================
accuracy=0.967
precision=0.824
recall=1.000
f1=0.903
======================================
Ditto (with both dk and da)
=========eval at epoch=40=========
Validation:
=============Structured/Beer==================
accuracy=0.956
precision=0.857
recall=0.857
f1=0.857
======================================
Test:
=============Structured/Beer==================
accuracy=0.978
precision=0.875
recall=1.000
f1=0.933
======================================
In the paper's experiments, we reported the results by taking the epoch with the highest validation F1 score (here I am taking the last epoch).
I did notice something strange as the baseline result seems significantly higher than before. I remember that we updated the MixDA code from snippext which might have some effect on the data augmentation results too.
from ditto.
Thank you!
from ditto.
Related Issues (20)
- Code implementation - Training HOT 9
- ImportError: cannot import name 'LongformerModel' from 'transformers' (transformers=2.8)
- How is your F1 score calculated, whether you use weight or macro or micro HOT 1
- random result when inference 2 similar textual data HOT 3
- Add --save_model flag to the training example
- Error when using --summarize with matcher.py HOT 1
- Whether are special tokens like [COL] [VAL] and attribute names added into the vocabulary?
- [Question] Can I use this package in a notebook environment?
- Inferencing HOT 1
- How (code) to serialize the inputs ? HOT 1
- ModuleNotFoundError: No module named 'click._bashcomplete' HOT 1
- ValueError: not enough values to unpack (expected 2, got 1) - Textual/Company HOT 5
- drop_col gives error? HOT 5
- Which f1 should we report? HOT 1
- evaluation method seems to assign a new f1 value as a best score without computing f1 value by best_th=0.5 HOT 1
- Adding custom tokens
- F1 Score for Structured/Beer on paper can't be reproduced
- The link for the Company.zip file seems to be invalid. HOT 1
- Summarization sometimes removes attribute names between [COL] and [VAL]
- training HOT 7
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 ditto.