Learning Explanations from Language Data

Autor:	Harbecke, David, Schwarzenberg, Robert, Alt, Christoph
Rok vydání:	2018
Předmět:	Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	PatternAttribution is a recent method, introduced in the vision domain, that explains classifications of deep neural networks. We demonstrate that it also generates meaningful interpretations in the language domain. Comment: Appears in 2018 EMNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1808.04127 Zobrazit plný text záznamu View this record from Arxiv