claritylab/MARS-Encoder

MARS Encoder for Multi-Agent Response Selection

This model was trained using SentenceTransformers Cross-Encoder class and is the model used in the paper One Agent To Rule Them All: Towards Multi-agent Conversational AI.

Training Data

This model was trained on the BBAI dataset. The model will predict a score between 0 and 1 ranking the correctness of a response to a user question from a conversational agent.

Usage and Performance

Pre-trained models can be used like this:

from sentence_transformers import CrossEncoder
model = CrossEncoder('csclarke/MARS-Encoder')
scores = model.predict([('question 1', 'response 1'), ('question 1', 'response 2')])

The model will predict scores for the pairs ('question 1', 'response 1') and ('question 1', 'response 2').

You can use this model also without sentence_transformers and by just using Transformers AutoModel class