Question 1

What is the Situated and Interactive Multimodal Conversations (SIMMC) dataset?

Accepted Answer

There are 2 datasets totalling ∼13K human-human dialogs (∼169K utterances) using a multimodal Wizard-of-Oz (WoZ) setup, on two shopping domains: (a) furniture (grounded in a shared virtual environment) and, (b) fashion (grounded in an evolving set of images).

Question 2

Is Situated and Interactive Multimodal Conversations (SIMMC) a benchmark?

Accepted Answer

Situated and Interactive Multimodal Conversations (SIMMC) is a dataset for training or evaluation; it isn't tracked as a standard LLM benchmark in our catalog.

Question 3

Where can I download Situated and Interactive Multimodal Conversations (SIMMC)?

Accepted Answer

Situated and Interactive Multimodal Conversations (SIMMC) is available at its source: https://github.com/facebookresearch/simmc?fbclid=IwAR0QZDXnrSAWiuCjvfev4n6P9XA7cSHRNOkXzLg7nCa-9P9BhO0VnOTxF0c.

Situated and Interactive Multimodal Conversations (SIMMC)

About Situated and Interactive Multimodal Conversations (SIMMC)

Details

FAQ