从语言数据中学习解释
计算与语言
2018-08-14 v1 机器学习
摘要
PatternAttribution 是近期在视觉领域提出的一种解释深度神经网络分类结果的方法。我们证明它也能在语言领域生成有意义的解释。
引用
@article{arxiv.1808.04127,
title = {Learning Explanations from Language Data},
author = {David Harbecke and Robert Schwarzenberg and Christoph Alt},
journal= {arXiv preprint arXiv:1808.04127},
year = {2018}
}
备注
Appears in 2018 EMNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)