OpenNMT/OpenNMT-tf

Copy Attention feature is needed

Open

#95 创建于 2018年4月2日

在 GitHub 查看
 (3 评论) (0 反应) (0 负责人)Python (1,428 star) (394 fork)batch import
enhancementhelp wanted

描述

Opennmt-py has Copy Attention feature, which is very useful mechanism for many applications. Is there any plan to add this feature on Opennmt-tf? The link of copy attention in opennmt-py, http://opennmt.net/OpenNMT-py/onmt.modules.html?highlight=copy#copy-attention

贡献者指南

技术栈
python
领域
machine learningai
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
4
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
over 1 week
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
knowledge of attention mechanismsfamiliarity with TensorFlowunderstanding of OpenNMT tf codebase
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
20
研究方向
The issue requests adding a copy attention mechanism similar to OpenNMT py (reference: http://opennmt.net/OpenNMT py/onmt.modules.html?highlight=copy#copy attention). To implement, first study the copy attention implementation in OpenNMT py's source code, then explore OpenNMT tf's model structure (likely in the 'models' or 'layers' directory) to identify where to integrate. Check existing attention implementations in OpenNMT tf to understand the pattern. No linked PRs or assignees, so the feature is available for implementation.