This dataset provides a set of non-shoppable items, which are items that can't be purchased via a virtual assistant (love, vampires, etc). 
In addition, for each non-shoppable item, the dataset contains humorous responses generated by two different large language models, and a template-based generation solution that uses a commonsense knowledge graph called ConceptNet.
Finally, each row contains a score provided by human annotators that judge how funny each response is.
The columns provided for each datapoint are as follows:
question- purchase request of the non-shoppable item
answer- a generated response
model- the name of the model or solution that generated the response
non_shoppable_item- the name of the non shoppable item
relation- commonsense relation that was used to generate the response in the template-based approach
prompt_or_template- the prompt that was used to generate the responses
score- the average response score of the human evaluation

The dataset can be found at https://shopping-humor-generation.s3.amazonaws.com/ShoppingHumorGenDataset.zip


To see the full description, please see:
Natalie Shapira, Oren Kalinsky, Alexander Libov, Chen Shani, and Sofia Tolmach, Evaluating Humorous Response Generation to Playful Shopping Requests, ECIR 2023.