arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.04063cs.CLstat.ML
收藏

NLP的神经网络分析与解释--首届BlackboxNLP研讨会报告

Analyzing and Interpreting Neural Networks for NLP: A Report on the First BlackboxNLP Workshop

Tilburg University(蒂尔堡大学);Johns Hopkins University(约翰斯·霍普金斯大学)

Afra Alishahi, Grzegorz Chrupała, Tal Linzen

摘要:

EMNLP 2018研讨会BlackboxNLP致力于专门开发的资源和技术,用于分析和理解语言神经模型获得的内部工作和表示。办法包括:系统地操纵神经网络的输入并调查对其性能的影响,测试可解释的知识是否可以从神经网络获得的中间表示中解码,提出对神经网络架构的修改以使其知识状态或生成的输出更可解释,并检查简化或形式语言上的网络性能。在这里,我们回顾了每个类别中的一些代表性研究。

英文摘要:

The EMNLP 2018 workshop BlackboxNLP was dedicated to resources and techniques specifically developed for analyzing and understanding the inner-workings and representations acquired by neural models of language. Approaches included: systematic manipulation of input to neural networks and investigating the impact on their performance, testing whether interpretable knowledge can be decoded from intermediate representations acquired by neural networks, proposing modifications to neural network architectures to make their knowledge state or generated output more explainable, and examining the performance of networks on simplified or formal languages. Here we review a number of representative studies in each category.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑