Models
Concepts
See all articlesWhat are models on Tekst?
Models are the part of Tekst that reads each incoming message and turns it into something your automations can act on...
See more
What data does Tekst store and how does the learning process work?
Tekst processes customer data using a streaming architecture: the content of emails, tickets, and cases is handled ep...
See more
How is model accuracy calculated?
Monitoring model and tag accuracy ensures your models and, therefore, your automations are performing as well as poss...
See more
Which AI models are used for real-time processing?
To maximize processing speed and minimize the risk of failures or delays, our platform uses an intelligent, dynamic m...
See more
How often are the AI models retrained?
The training of custom models is fully managed by Tekst. Every customer has multiple models that are constantly monit...
See more
Supported languages
Tekst is not limited to a fixed set of languages. Our models work across scripts and language families, including Cyr...
See more
Classification
See all articlesEvaluate a classification model
Evaluating a classification model is how you check whether it is labeling conversations correctly. Tekst walks you th...
See more
What is a classification model?
A classification model reads an incoming message and assigns it one or more predefined labels based on its content. I...
See more
Set up your first classification model
This article walks you through creating a classification model from scratch, from naming it to measuring its accuracy...
See more
How classification accuracy is measured
Tekst measures how well a classification model is performing by comparing its predictions against a test set of valid...
See more
Extraction
See all articlesEvaluate an extraction model
Evaluating an extraction model is how you check whether it is pulling the right values out of your conversations and ...
See more
What is an extraction model?
An extraction model reads an incoming message and its attachments and pulls out specific pieces of structured data - ...
See more
Set up your first extraction model
This article walks you through creating an extraction model, from naming it to measuring its accuracy. If you are not...
See more
How extraction accuracy is measured
Tekst measures how well an extraction model is performing by comparing the values it predicts against a test set of v...
See more
Matching
See all articlesWhat is a matching model?
A matching model compares an incoming message against your own master data records and returns the single best match....
See more
Using domain knowledge to guide matching
Domain knowledge is where you capture the human context a matching model needs to choose the right record - the synon...
See more
Set up your first matching model
This article walks you through creating a matching model, from importing your records to measuring its accuracy. If y...
See more
Managing master data records
The records you import into a matching model are the reference data it matches incoming messages against - your produ...
See more
How matching accuracy is measured
Tekst measures how well a matching model is performing by comparing the record it picks against a test set of validat...
See more