作者
Kaylee Burns, Aida Nematzadeh, Erin Grant, Alison Gopnik, Tom Griffiths
发表日期
2018
期刊
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
页码范围
378-380
简介
The decision making processes of deep networks are difficult to understand and while their accuracy often improves with increased architectural complexity, so too does their opacity. Practical use of machine learning models, especially for question and answering applications, demands a system that is interpretable. We analyze the attention of a memory network model to reconcile contradictory performance on a challenging question-answering dataset that is inspired by theory-of-mind experiments. We equate success on questions to task classification, which explains not only test-time failures but also how well the model generalizes to new training conditions.
学术搜索中的文章
K Burns, A Nematzadeh, E Grant, A Gopnik, T Griffiths - Proceedings of the 2018 EMNLP Workshop …, 2018