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]

Authors

Mario Giulianelli

This author has not been identified. Look up 'Mario Giulianelli' in Google

Jack Harding

This author has not been identified. Look up 'Jack Harding' in Google

Florian Mohnert

This author has not been identified. Look up 'Florian Mohnert' in Google

Dieuwke Hupkes

This author has not been identified. Look up 'Dieuwke Hupkes' in Google

Willem H. Zuidema

This author has not been identified. Look up 'Willem H. Zuidema' in Google