full 0.0.3.1

No project description provided

FULL

Unsupervised evaluation of open-domain conversations using follow-ups likelihood.

---

Installation

pip install full

Example

We provide an example script using FULL which reproduces the results of the paper.

Turn evaluation

from full import FULL
eval_model = FULL()
conversation = ["Hi", "What's your name"]
response = "None of your business"
evaluation = eval_model.evaluate_turn(convesation, response)
print(evaluation)

Conversation evaluation

from full import FULL
eval_model = FULL()
conversation = ["Hi", "What's your name", "None of your business"]
evaluation = eval_model.evaluate_turn(convesation)
print(evaluation)

License

full is distributed under the terms of the MIT license.