Base model: roberta-large

Fine tuned as a progression model (to predict the acceptability of a dialogue) on the Persuasion For Good Dataset (Wang et al., 2019):

Given a complete dialogue from (or in the style of) Persuasion For Good, the task is to predict a numeric score typically in the range (-3, 3) where a higher score means a more acceptable dialogue in context of the donation solicitation task.

Example input: How are you?</s>Good! how about yourself?</s>Great. Would you like to donate today to help the children?</s>

For more context and usage information see https://github.rpi.edu/LACAI/dialogue-progression.

Downloads last month
30
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.