Attending Knowledge Facts with BERT-like Models in Question-Answering: Disappointing Results and Some Explanations

Guillaume Le Berre, Philippe Langlais. Attending Knowledge Facts with BERT-like Models in Question-Answering: Disappointing Results and Some Explanations. In Cyril Goutte, Xiaodan Zhu, editors, Advances in Artificial Intelligence - 33rd Canadian Conference on Artificial Intelligence, Canadian AI 2020, Ottawa, ON, Canada, May 13-15, 2020, Proceedings. Volume 12109 of Lecture Notes in Computer Science, pages 356-367, Springer, 2020. [doi]

@inproceedings{BerreL20,
  title = {Attending Knowledge Facts with BERT-like Models in Question-Answering: Disappointing Results and Some Explanations},
  author = {Guillaume Le Berre and Philippe Langlais},
  year = {2020},
  doi = {10.1007/978-3-030-47358-7_37},
  url = {https://doi.org/10.1007/978-3-030-47358-7_37},
  researchr = {https://researchr.org/publication/BerreL20},
  cites = {0},
  citedby = {0},
  pages = {356-367},
  booktitle = {Advances in Artificial Intelligence - 33rd Canadian Conference on Artificial Intelligence, Canadian AI 2020, Ottawa, ON, Canada, May 13-15, 2020, Proceedings},
  editor = {Cyril Goutte and Xiaodan Zhu},
  volume = {12109},
  series = {Lecture Notes in Computer Science},
  publisher = {Springer},
  isbn = {978-3-030-47358-7},
}