COLING 2020main66 citations
Do Neural Language Models Overcome Reporting Bias?
Abstract
Mining commonsense knowledge from corpora suffers from reporting bias, over-representing the rare at the expense of the trivial (Gordon and Van Durme, 2013). We study to what extent pre-trained language models overcome this issue. We find that while their generalization capacity allows them to better estimate the plausibility of frequent but unspoken of actions, outcomes, and properties, they also tend to overestimate that of the very rare, amplifying the bias that already exists in their training corpus.
BibTeX
@inproceedings{shwartz-choi-2020-neural,
title = "Do Neural Language Models Overcome Reporting Bias?",
author = "Shwartz, Vered and
Choi, Yejin",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.605/",
doi = "10.18653/v1/2020.coling-main.605",
pages = "6863--6870"
}