OpenNMT/OpenNMT-tf

Coverage Mechanism and Coverage Loss

Open

#180 建立於 2018年7月25日

在 GitHub 查看
 (8 留言) (5 反應) (0 負責人)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!

貢獻者指南

技術棧
pythontensorflow
領域
machine learning
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
4
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
over 1 week
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
Understanding of attention mechanismsTensorFlow basicsseq2seq models
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
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.