A curated list of awesome knowledge graph tutorials, projects and communities.
736
stars
120
forks
source link
WMT-2018-An Analysis of Attention Mechanisms: The Case of Word Sense Disambiguation in Neural Machine Translation #238
Open
BrambleXu opened 5 years ago
一句话总结：
针对NMT任务的分析文章，关于analysis of multi-head attention 的部分，focused only on the maximum attention weights. #235 引用了
资源：
论文信息：
笔记：
模型图：
结果：
接下来要看的论文：