In this step, we create our first model. You can either use promptranker to help you find the best labels and hypotheses or skip this step with your preferred setting.
...
| Info |
|---|
As a brief reminder, when defining the text classification task, we need to associate a label text (the label description) with the label name (the actual label) that we are intending to categorise. This label text, also referred sometimes as hypothesis or prompt, provides a semantic context to the model. |
...
2. Select the number of labels you want to have using the slider
3. Continue with/ without using Promptranker
| Expand |
|---|
| title | If you want to continue without using Promptranker: |
|---|
|
3. Provide label names, e.g. |
...
...
| and label texts (hypotheses), e.g. |
...
...
...
label name in the label text too, such as |
...
...
 Image Modified| Info |
|---|
Please note: Hypotheses could also be long and detailed explanations of your labels, e.g. if your labels come from a specific framework you can use the framework’s description of each label with/ or multiple descriptors (adjectives/ nouns for more clarity). When formulating long hypotheses always think about what would help another person to understand my label better in order to end up with the most clear and understandable hypothesis. |
2. Enable ‘Inspect typical examples’ to see how your model performs Image Modified 2.1. Use the slider to select up to 10 examples. 2.2. Change the label dropdown to see examples for each of your labels. 2.3. Change the assigned label if necessary 3. Click Create |
| Expand |
|---|
| title | If you want to continue using Promptranker: |
|---|
|
| Info |
|---|
This will run an unsupervised statistical Bayesian process that will end up outputting a reliability score of the best combination from the provided ones. It is recommended to use that combination for your model, both at zero and few-shot level. |
Enable ‘Rank label texts’ Provide label names, e.g. , For each label name, provide a list of alternative descriptions. For example, for positive, you can provide and for negative,
Provide hypothesis variations, e.g. use an empty one and add several different variations such as , | Status |
|---|
| title | The author expresses a {} sentiment |
|---|
|
, …
 Image ModifiedThe result is a table where each variation is ranked according to a calculated score. The higher the score, the more likely the given labels and hypothesis yield good results in a real scenario.  Image Modified4. Click Create and the model will be automatically created with the prompts (labels and hypothesis) that scored the top. |
...