Analysing Neural Language Models: Contextual Decomposition Reveals Default Reasoning in Number and Gender Assignment

Jaap Jumelet; Willem Zuidema; Dieuwke Hupkes

2019 CoNLL CoNLL 2019

Analysing Neural Language Models: Contextual Decomposition Reveals Default Reasoning in Number and Gender Assignment

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Jaap Jumelet, Willem Zuidema, Dieuwke Hupkes

Topics

Artificial Intelligence > Core AI > Interpretability Natural Language Processing > Generation > Language Modeling

Keywords

long short-term memory recurrent neural network neural language model interpretability analysis contextual decomposition number prediction syntactic agreement gender assignment

Download PDF