Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information

Mario Giulianelli, Jack Harding, Florian Mohnert, Dieuwke Hupkes, Willem H. Zuidema. Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information. In Tal Linzen, Grzegorz Chrupala, Afra Alishahi, editors, Proceedings of the Workshop: Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2018, Brussels, Belgium, November 1, 2018. pages 240-248, Association for Computational Linguistics, 2018. [doi]

@inproceedings{GiulianelliHMHZ18,
  title = {Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information},
  author = {Mario Giulianelli and Jack Harding and Florian Mohnert and Dieuwke Hupkes and Willem H. Zuidema},
  year = {2018},
  url = {https://aclanthology.info/papers/W18-5426/w18-5426},
  researchr = {https://researchr.org/publication/GiulianelliHMHZ18},
  cites = {0},
  citedby = {0},
  pages = {240-248},
  booktitle = {Proceedings of the Workshop: Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2018, Brussels, Belgium, November 1, 2018},
  editor = {Tal Linzen and Grzegorz Chrupala and Afra Alishahi},
  publisher = {Association for Computational Linguistics},
  isbn = {978-1-948087-71-1},
}