Published October 20, 2023
| Version v1
Dataset
Open
whatsnext-scores
- 1. University of Amsterdam
-
2.
IT University of Copenhagen
- 3. MCML Munich
-
4.
Ludwig-Maximilians-Universität München
Description
This dataset contains production variability scores as described in the following paper:
Mario Giulianelli, Joris Baan, Wilker Aziz, Raquel Fernández, and Barbara Plank. 2023. What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
We make these scores available to facilitate the reproducibility of our experiments, which can be found at https://github.com/dmg-illc/nlg-uncertainty-probes.
Files
Files
(2.4 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:4f765f072cfc2dab29d466075885dd27
|
2.4 GB | Download |
Additional details
Funding
- European Commission
- DREAM – Distributed dynamic REpresentations for diAlogue Management 819455
- European Commission
- UTTER – Unified Transcription and Translation for Extended Reality 101070631
- European Commission
- DIALECT – Natural Language Understanding for non-standard languages and dialects 101043235