Google

In probabilistic classification, a model's output is a probability distribution over a set of possible labels. To determine the final prediction, a decision rule is applied which selects the single label that corresponds to the highest probability within this distribution.

Maximum Probability Decision Rule

Once a model's parameters have been optimized through fine-tuning, the resulting model, denoted as $$F_{\tilde{\omega},\tilde{\theta}}(\cdot)$$, can be used for inference on new, unseen data. For instance, in a text classification task, the new text is first tokenized into a sequence of tokens, represented as $$\mathbf{x}_{\mathrm{new}}$$. This token sequence is then fed into the fine-tuned model, which processes it to generate a probability distribution over the possible classes.

Inference Process with a Fine-Tuned Model

For each ticket ID in the case study below, determine the single category that the model will predict. In your answer, also provide a brief explanation for how you determined the category for Ticket ID #2.

Customer Support Ticket Classification

A classification model has analyzed an input and produced a set of probabilities, with each probability corresponding to a different possible category. Describe the procedure used to select a single, final category prediction from this set of probabilities.

Explaining the Prediction Rule

A probabilistic model is designed to classify news headlines into one of four categories: 'Business', 'Technology', 'Sports', or 'Health'. For a new headline, the model outputs the following probability distribution:

- Business: 0.12
- Technology: 0.25
- Sports: 0.55
- Health: 0.08

Based on the most common decision rule for converting these probabilities into a single prediction, which category will be assigned to the headline?

Learn Before

Related