README.md

metadata

license: mit
language:
  - en
pipeline_tag: fill-mask
library_name: transformers
widget:
  - text: The boy was <mask>.
    example_title: Example 1
  - text: The cat started to <mask>.
    example_title: Example 2
  - text: The <mask> girl was eating.
    example_title: Example 3

roberta-poetry-happiness-crpo

This model is based on the RoBERTa base model (125 M parameters) fine-tuned on a poetry corpus selected automatically to reflect happy emotions.

The model replaces a masked word, indicated by the <mask> tag, with a word associated with happiness, while preserving fluency.

This model was trained by Teo Ferrari as part of his Bachelor thesis at HEIG-VD, supervised by Andrei Popescu-Belis. The model is described in "GPoeT: a Language Model Trained for Rhyme Generation on Synthetic Data" and is used in the CR-PO system for interactive poem generation, along with several other models for specific topics or emotions.