- Introduction
- Setting up your account
- Balance
- Clusters
- Concept drift
- Coverage
- Datasets
- General fields
- Labels (predictions, confidence levels, label hierarchy, and label sentiment)
- Models
- Streams
- Model Rating
- Projects
- Precision
- Recall
- Annotated and unannotated messages
- Extraction Fields
- Sources
- Taxonomies
- Training
- True and false positive and negative predictions
- Validation
- Messages
- Access Control and Administration
- Manage sources and datasets
- Understanding the data structure and permissions
- Creating or deleting a data source in the GUI
- Uploading a CSV file into a source
- Preparing data for .CSV upload
- Creating a dataset
- Multilingual sources and datasets
- Enabling sentiment on a dataset
- Amending dataset settings
- Deleting a message
- Deleting a dataset
- Exporting a dataset
- Using Exchange integrations
- Model training and maintenance
- Understanding labels, general fields, and metadata
- Label hierarchy and best practices
- Comparing analytics and automation use cases
- Turning your objectives into labels
- Overview of the model training process
- Generative Annotation
- Dastaset status
- Model training and annotating best practice
- Training with label sentiment analysis enabled
- Training chat and calls data
- Understanding data requirements
- Train
- Introduction to Refine
- Precision and recall explained
- Precision and Recall
- How validation works
- Understanding and improving model performance
- Reasons for label 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™
- Developer
- Exchange Integration with Azure service user
- Exchange Integration with Azure Application Authentication
- Exchange Integration with Azure Application Authentication and Graph
- Fetching data for Tableau with Python
- Elasticsearch integration
- Self-hosted Exchange integration
- UiPath® Automation Framework
- UiPath® Marketplace activities
- UiPath® official activities
- How machines learn to understand words: a guide to embeddings in NLP
- Prompt-based learning with Transformers
- Efficient Transformers II: knowledge distillation & fine-tuning
- Efficient Transformers I: attention mechanisms
- Deep hierarchical unsupervised intent modelling: getting value without training data
- Fixing annotating bias with Communications Mining™
- Active learning: better ML models in less time
- It's all in the numbers - assessing model performance with metrics
- Why model validation is important
- Comparing Communications Mining™ and Google AutoML for conversational data intelligence
- Licensing
- FAQs and more
Communications Mining user guide
Training using Low confidence
The final key step in Explore is training using the Low confidence mode, which shows you messages that are not well covered by informative label predictions. These messages will have either no predictions or very low confidence predictions for labels that the platform understands to be informative.
Informative labels are those labels that the platform understands to be useful as standalone labels, by looking at how frequently they are assigned with other labels.
This is a very important step for improving the overall coverage of your model. If you see messages which should have existing labels predicted for them, this is a sign that you need to complete more training for those labels. If you identify relevant messages for which no current label is applicable, you may want to create new labels to capture them.
To access the Low confidence mode, use the dropdown menu from the Explore page, as shown in the following image:
The Low confidence mode will present you with 20 messages at a time, and you should complete a reasonable amount of training in this mode, going through multiple pages of messages and applying the correct labels, to help increase the coverage of the model. For a detailed explanation of coverage, check When to stop training your model.
The total amount of training you need to complete in Low confidence depends on a few different factors:
- How much training you completed in Shuffle and Teach. The more training you do in Shuffle and Teach, the more your training set should be a representative sample of the dataset as a whole, and the fewer relevant messages there should be in Low confidence.
- The purpose of the dataset. If the dataset is intended to be used for automation and requires very high coverage, then you should complete a larger proportion of training in Low confidence to identify the various edge cases for each label.
At a minimum, you should aim to annotate five pages of messages in this mode. Later on in the Refine phase when you come to check your coverage, you may find that you need to complete more training in Low confidence to improve your coverage further.
