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

Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information Mario Giulianelli author Jack Harding author Florian Mohnert author Dieuwke Hupkes author Willem Zuidema author 2018-11 text Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP Tal Linzen editor Grzegorz Chrupała editor Afra Alishahi editor Association for Computational Linguistics Brussels, Belgium conference publication giulianelli-etal-2018-hood 10.18653/v1/W18-5426 https://aclanthology.org/W18-5426/ 2018-11 240 248