ICAR Research Data Repository for Knowledge Management
EnronSR: A Benchmark for Evaluating AI-Generated Email Replies
Harvard Dataverse (Africa Rice Center, Bioversity International, CCAFS, CIAT, IFPRI, IRRI and WorldFish)
View Archive Info| Field | Value | |
| Title |
EnronSR: A Benchmark for Evaluating AI-Generated Email Replies
|
|
| Identifier |
https://doi.org/10.7910/DVN/RQBWAC
|
|
| Creator |
Shay, Moran
Davidson, Roei Grinberg, Nir |
|
| Publisher |
Harvard Dataverse
|
|
| Description |
EnronSR, is a benchmark dataset based on the Enron email corpus that contains both naturally occurring human- and AI-generated email replies for the same set of messages. This resource enables the public benchmarking of novel language-generation models and facilitates a comparison against the strong, production-level baseline of Google Smart Reply used by millions of people.
|
|
| Subject |
Computer and Information Science
Engineering Social Sciences AI-MC Bias Natural Language Generation Benchmark dataset |
|
| Date |
2024-01-15
|
|
| Contributor |
Grinberg, Nir
|
|