Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge

Ian Porada, Alessandro Sordoni, Jackie Chi Kit Cheung. Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge. In Marine Carpuat, Marie-Catherine de Marneffe, Iván Vladimir Meza Ruíz, editors, Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United States, July 10-15, 2022. pages 4550-4557, Association for Computational Linguistics, 2022. [doi]

@inproceedings{PoradaSC22,
  title = {Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge},
  author = {Ian Porada and Alessandro Sordoni and Jackie Chi Kit Cheung},
  year = {2022},
  url = {https://aclanthology.org/2022.naacl-main.337},
  researchr = {https://researchr.org/publication/PoradaSC22},
  cites = {0},
  citedby = {0},
  pages = {4550-4557},
  booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United States, July 10-15, 2022},
  editor = {Marine Carpuat and Marie-Catherine de Marneffe and Iván Vladimir Meza Ruíz},
  publisher = {Association for Computational Linguistics},
  isbn = {978-1-955917-71-1},
}