Abstract
Open-domain dialogue systems aim to converse with humans through text, and dialogue research has heavily relied on benchmark datasets. In this work, we observe the overlapping problem in DailyDialog and OpenSubtitles, two popular open-domain dialogue benchmark datasets. Our systematic analysis then shows that such overlapping can be exploited to obtain fake state-of-the-art performance. Finally, we address this issue by cleaning these datasets and setting up a proper data processing procedure for future research.- Anthology ID:
- 2022.lrec-1.16
- Volume:
- Proceedings of the Thirteenth Language Resources and Evaluation Conference
- Month:
- June
- Year:
- 2022
- Address:
- Marseille, France
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 146–153
- Language:
- URL:
- https://aclanthology.org/2022.lrec-1.16
- DOI:
- Cite (ACL):
- Yuqiao Wen, Guoqing Luo, and Lili Mou. 2022. An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasets. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 146–153, Marseille, France. European Language Resources Association.
- Cite (Informal):
- An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasets (Wen et al., LREC 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.lrec-1.16.pdf
- Code
- yq-wen/overlapping-datasets
- Data
- ATIS