@inproceedings{agrawal-singh-2023-corpus,
title = "Corpus Complexity Matters in Pretraining Language Models",
author = "Agrawal, Ameeta and
Singh, Suresh",
editor = "Sadat Moosavi, Nafise and
Gurevych, Iryna and
Hou, Yufang and
Kim, Gyuwan and
Kim, Young Jin and
Schuster, Tal and
Agrawal, Ameeta",
booktitle = "Proceedings of the Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP)",
month = jul,
year = "2023",
address = "Toronto, Canada (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/fix-sig-urls/2023.sustainlp-1.20/",
doi = "10.18653/v1/2023.sustainlp-1.20",
pages = "257--263"
}
Markdown (Informal)
[Corpus Complexity Matters in Pretraining Language Models](https://preview.aclanthology.org/fix-sig-urls/2023.sustainlp-1.20/) (Agrawal & Singh, sustainlp 2023)
ACL
- Ameeta Agrawal and Suresh Singh. 2023. Corpus Complexity Matters in Pretraining Language Models. In Proceedings of the Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP), pages 257–263, Toronto, Canada (Hybrid). Association for Computational Linguistics.