Comments (5)
soodeh-nilforoushan
commented on July 20, 2024
When I try to use data augmentation with drop_col, I get the error below. I did not change anything about the model or data, is there something I'm missing?
did you solve the problem? I got the same error
from ditto.
utsgr
commented on July 20, 2024
Sadly no, I'm hoping someone can help.
from ditto.
soodeh-nilforoushan
commented on July 20, 2024
Sadly no, I'm hoping someone can help.
They added the ditto light on their code, and after this changes, this error happens. I hope authors answer this question
from ditto.
progsi
commented on July 20, 2024
Problem appears to be that they are using \t instead of [SEP]. Also, the variable combined is split as well and by just ignoring this line of code it seems to work for me.
from ditto.
rinkstiekema
commented on July 20, 2024
I do not think the issue is caused by using \t instead of [SEP] as that is also used in the other data augmentation functions. I noticed a different pattern; if the column before the separator is the one to be removed, it also removes the [SEP] indicator from the resulting tokens.
I'll attempt to fix the algorithm for dropping columns, I'll keep you posted.
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
- 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.
- 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.