๐Ÿ”Ž Explainability and bias#

These tutorials show you how to explain you data using Argilla.

๐Ÿ—บ๏ธ Adding bias-equality features to text with disaggregators

MLOps Steps: Labelling
NLP Tasks: Text2Text
Libraries: Disaggregators
Techniques: Explainability

๐Ÿ” Backup and version Argilla Datasets using DVC

MLOps Steps: Deploying, Monitoring
NLP Tasks: Text2Text
Libraries: dvc
Techniques: Explainability

๐Ÿง Find label errors with cleanlab

MLOps Steps: Training, Monitoring
NLP Tasks: TextClassification
Libraries: cleanlab
Techniques: explainability

๐Ÿ•ต๏ธโ€โ™€๏ธ Analyzing predictions with model explainability methods

MLOps Steps: Monitoring
NLP Tasks: TextClassification
Libraries: shap, transformers-interpret
Techniques: Explainability

๐Ÿ’ก Building and testing a zero-shot sentiment classifier with GPT-3 and Argilla

MLOps Steps: Labelling
NLP Tasks: TextClassification
Libraries: OpenAI
Techniques: Few-shot, Explainability

๐Ÿงผ Clean labels using your model loss

MLOps Steps: Monitoring
NLP Tasks: TextClassification
Libraries: Argilla, transformers
Techniques: Explainability

๐Ÿ’ซ Explore and analyze spaCy NER pipelines

MLOps Steps: Labelling
NLP Tasks: TokenClassification (NER)
Libraries: spaCy
Techniques: Explainability

๐Ÿ’ก Building and testing a zero-shot sentiment classifier with GPT-3 and Argilla

MLOps Steps: Labelling
NLP Tasks: TextClassification
Libraries: OpenAI
Techniques: Few-shot, Explainability