interpret-text
interpret-text copied to clipboard
interpretml
A library that incorporates state-of-the-art explainers for text-based machine learning models and visualizes the result with a built-in dashboard.
setup.py depends on most dependencies but the conda install from tools/ resolves an issue taht pip requirements do not. An example of a failed build: https://dev.azure.com/responsibleai/interpret-text/_build/results?buildId=5720&view=logs&j=cac13d19-97dc-52d6-a58d-dbc7d5c3ddc1&t=ec6b3cec-d324-59f0-bb1a-6e83d32ca2c2
 [cls] and [sep] should not show up. Also the label doesn't change and the anti-rationales, which would have been the neg feat. importance are not passed into the...
AttributeError Traceback (most recent call last) /tmp/ipykernel_34754/2258094842.py in ----> 1 ResponsibleAIDashboard(rai_insights, cohort_list=cohort_list) ~/.conda/envs/response1/lib/python3.7/site-packages/raiwidgets/responsibleai_dashboard.py in __init__(self, analysis, public_ip, port, locale, cohort_list, **kwargs) 33 cohort_list=None, **kwargs): 34 self.input = ResponsibleAIDashboardInput( ---> 35...
The API and functions used by in the notebooks do not work with Open AI 1.x.
Hi community, Any thoughts on how we can get some of the lime tool explainers to work on the Open AI Chat Completion models? Any advise or help appreciated. Thanks,...
Hello, I have a pre-trained model for text sentiment polarity classification, with a structure roughly composed of RoBERTa+TextCNN. Can I use the Introspective Rationale Explainer to interpret its output? I...
Do you consider supporting multi-label classification(one sample can have more than one label) using IntrospectiveRationaleExplainer? Right now IntrospectiveRationaleExplainer model can do multi-class classification task. What if we have training dataset...
Metadata
Owner
Metadata
A library that incorporates state-of-the-art explainers for text-based machine learning models and visualizes the result with a built-in dashboard.