- Getting started
- Balance
- Clusters
- Concept drift
- Coverage
- Datasets
- General fields (previously entities)
- Labels (predictions, confidence levels, hierarchy, etc.)
- Models
- Streams
- Model Rating
- Projects
- Precision
- Recall
- Reviewed and unreviewed messages
- Sources
- Taxonomies
- Training
- True and false positive and negative predictions
- Validation
- Messages
- Administration
- Manage sources and datasets
- Understanding the data structure and permissions
- Create a data source in the GUI
- Uploading a CSV file into a source
- Create a new dataset
- Multilingual sources and datasets
- Enabling sentiment on a dataset
- Amend a dataset's settings
- Delete messages via the UI
- Delete a dataset
- Delete a source
- Export a dataset
- Using Exchange Integrations
- Preparing data for .CSV upload
- Model training and maintenance
- Understanding labels, general fields and metadata
- Label hierarchy and best practice
- Defining your taxonomy objectives
- Analytics vs. automation use cases
- Turning your objectives into labels
- Building your taxonomy structure
- Taxonomy design best practice
- Importing your taxonomy
- Overview of the model training process
- Generative Annotation (NEW)
- Dastaset status
- Model training and annotating best practice
- Training with label sentiment analysis enabled
- Train
- Introduction to Refine
- Precision and recall explained
- Precision and recall
- How does Validation work?
- Understanding and improving model performance
- Why might a label have low average precision?
- Training using Check label and Missed label
- Training using Teach label (Refine)
- Training using Search (Refine)
- Understanding and increasing coverage
- Improving Balance and using Rebalance
- When to stop training your model
- Using general fields
- Generative extraction
- Using analytics and monitoring
- Automations and Communications Mining
- Licensing information
- FAQs and more
Overview of the model training process
Training a model can be broken down into a three phase process:
In the first instance, it's good practice to go through these steps in order, but this can be an iterative process. You may find in time that for different labels, you may chop and change the different steps as you become more familiar with the platform.
Discover
Discover is where similar intents, patterns and conversation themes are grouped together into ‘clusters’. This is the starting point and is used to quickly build an initial model where you analyse your data and tag each cluster with one or more label that applies.
Explore
After reviewing clusters in Discover, Explore is used to further train your model. Most of your time will be spent here reviewing messages, adding labels, and improving the model’s understanding of your data.
Refine
This stage is used to assess and improve the overall performance of your model. In this stage, the platform provides guided feedback on the health of your model via the Model Rating, including performance issues and the next best actions to resolve them.
Discover, Explore and Refine phase can now be completed using the Train tab. For more information, see the Train page.
Prune / Re-organise
This is a part of the model training process that you can do at any time - renaming, merging or deleting labels as you go through the process. The process is explained in detail in the Explore page.
