- API docs
- CLI
- Integration guides
- Blog
- 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
Streams
A stream (formerly known as a trigger) in the platform is essentially a tool for automatically creating a queue of messages, which satisfy specific label or metadata conditions.
Streams are frequently used in the platform to facilitate automated processing of requests, with the platform acting as the interpreter of an unstructured communication. The platform understands and adds structure to the communication and makes it available downstream for processing.
This queue is made available to downstream applications via the Communications Mining™ API endpoints. The outputs from the API are machine readable objects in JSON format, containing all of the associated metadata, message text, and the associated labels as structured data points.
