Welcome to autoBOT’s documentation¶
autoBOT is an autoML system for automatic explainable classification of texts. It includes automatically generated features at different granularities, evolved to offer optimal performance/explainability tradeoff.
Tutorial and first steps:
- Installation
- autoBOTLib library
- Feature types
- Using custom classifiers
- Using custom feature transformers
- Model persistence
- Obtaining underlying representations
- autoBOTLib CLI
- Singularity container for autoBOT
- Using custom background knowledge
- Using custom metrics
- Potentially interesting further work
- Releases
- autoBOT API
- Scaling up (SLING)
- Performance on shared tasks
Contents:
- autoBOTLib
- autoBOTLib package
- Submodules
- autoBOTLib.features_concepts module
- autoBOTLib.features_contextual module
- autoBOTLib.features_document_graph module
- autoBOTLib.features_keyword module
- autoBOTLib.features_sentence_embeddings module
- autoBOTLib.features_token_relations module
- autoBOTLib.features_topic module
- autoBOTLib.misc_helpers module
- autoBOTLib.misc_keyword_detection module
- autoBOTLib.optimization_engine module
- autoBOTLib.optimization_feature_constructors module
- autoBOTLib.optimization_metrics module
- autoBOTLib.optimization_random module
- autoBOTLib.optimization_utils module
- Module contents
- autoBOTLib package