Page Comparison

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.

...

Expand

title	If you want to continue without using Promptranker:

3. Provide label names, e.g.

Status

colour	Green
title	positiveJOY

,

Status

colour	Red
title	negativeSaD

and label texts (hypotheses), e.g.

Status

colour	Green
title	greatHappy, AmmUSED

,

Status

colour	Red
title	badUNhappy, DISAPPOINTED

. You can include your hypothesis label name in the label text too, such as

Status

colour	Green
title	The text is greatperson FEELS JOY

or

Status

colour	Red
title	the text is badPERSON FEELS SAD

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.

Status

colour	Blue
title	Optional

Enable ‘Inspect typical examples’ to see how your model performs

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:

Panel

panelIconId	1f4bb
panelIcon	:computer:
panelIconText	💻
bgColor	#FFF0B3

API Docs: https://api.symanto.net/active-learning/docs#/v2/rank_label_texts_v2_datasets_rank_label_text_post

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.
Status
title positive
,
Status
title negative
1. For each label name, provide a list of alternative descriptions. For example, for positive, you can provide
  Status
  title great
  Status
  title wonderful
  Status
  title positive
  and for negative,
  Status
  title bad
  Status
  title terrible
  Status
  title negative
Provide hypothesis variations, e.g. use an empty one and add several different variations such as
Status
title This TExt is {}
,
Status
title The author expresses a {} sentiment
, …

The 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.

4. Click Create and the model will be automatically created with the prompts (labels and hypothesis) that scored the top.

...

Versions Compared

Old Version 7

New Version 8

Key