OpenNMT/OpenNMT-tf

Coverage Mechanism and Coverage Loss

Open

#180 创建于 2018年7月25日

在 GitHub 查看
 (8 评论) (5 反应) (0 负责人)Python (1,428 star) (394 fork)batch import
enhancementhelp wanted

描述

May I ask if there is any plan adding the coverage attention mechanism (https://arxiv.org/pdf/1601.04811.pdf) and coverage loss (https://arxiv.org/pdf/1704.04368.pdf) to the decoder, as these could potentially help alleviating the repetition problem in generation?

Or, any hints on a quick implementation? Thanks!

贡献者指南

技术栈
pythontensorflow
领域
machine learning
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
Understanding of attention mechanismsTensorFlow basicsseq2seq models
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。
25
研究方向
Review the decoder implementation in OpenNMT tf (likely in the 'opennmt/decoders' directory) to understand the current attention mechanism, then implement coverage attention as described in See et al. (2016) and coverage loss as in Tu et al. (2017). Check the issue comments for any prior discussion on implementation details or code references.