Comments (1)
Hi @hardianlawi, this is an interesting question. The short answer is that I think what you would like to do is possible. While the tokenized text is not super UX friendly it's important to remember that that tokenized text IS what the model is fed as input so attribution with respect to the tokens is for me the best way to try and represent the model's behaviour.
Bert like models tend to use the wordpiece method for tokenization and there are times in the explainer when you can see a model giving a negative attribution to the starting word piece and positive attribution to the negative wordpiece. For researchers and ML users interpreting their model's this could be quite useful information. To get rid of this information would be detrimental to the true interpretation of what is happening with the model.
I don't personally think I will implement a feature for mapping the attributions back to the exact text, or at least I'll have to think on it for a bit, but if you were to do this yourself you would just need to write some logic that could identify certain when a wordpiece occurs e.g. ["gp", "##u"]
and then you could average the two raw attributions for gp
and ##u
together for a single attribution score, this will then correspond back to the original text.
Hope this helps.
from transformers-interpret.
Related Issues (20)
- What algorithm is used to visualize text in SequenceClassificationExplainer
- How to use transformers-interpret for sequencelabelling, for example layoutlmv3 or v3 HOT 1
- MultiLabelSequenceClassificationExplainer potentially bugged. HOT 14
- ImportError: cannot import name 'PairwiseSequenceClassificationExplainer' HOT 1
- How to interpret the model fine tuning on the pre-trained ViT model using the imagery with larger resolution (500 * 500) than the pre-trained dataset (224 * 224)
- Token Classification Memory Issue
- Issue using BertTokenizer (AttributeError) HOT 2
- 'Bert' object has no attribute 'config'
- Text attribution fails for XLM-Roberta models HOT 4
- Is it normal that attribution takes multiple seconds per text, even on a GPU? HOT 1
- ZeroShotClassificationExplainer appears to be broken
- Prediction differs from non-explainable evaluation HOT 1
- Output probability - SequenceClassificationExplainer
- Support for Summarization models HOT 3
- Support for Longformer
- ImageClassificationExplainer: AttributeError: ndim when trying to visualize. HOT 3
- Issue with Zero Shot Classifier
- How to use other types of transformers models? HOT 1
- Support for Reformer
- Broken link for Captum Algorithm Overview in the README
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 transformers-interpret.