OpenNMT/OpenNMT-tf

Multi-decoder setup for multi-task learning

Open

#130 建立於 2018年5月22日

在 GitHub 查看
 (5 留言) (0 反應) (0 負責人)Python (1,428 star) (394 fork)batch import
enhancementhelp wanted

描述

Similarly to the ParallelEncoder, a ParallelDecoder setup could allow multi-task learning. This should not be too hard to implement but we need to take care of some details:

  • support separate values for the decoding parameters (beam_width, length_penalty, etc.),
  • parts of SequenceToSequence assume a single output head (e.g. loss computation, reverse vocabulary lookup, exported outputs for model serving, etc. which should be moved in the decoder itself)

貢獻者指南

技術棧
pythontensorflow
領域
machine learningai
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。
1-2 days
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
PythonTensorFlowsequence to sequence modelsOpenNMT tf codebase
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。
30
研究方向
Examine the existing `ParallelEncoder` implementation for guidance. Focus on the `SequenceToSequence` class to identify all components that assume a single output head, such as loss computation and reverse vocabulary lookup. Review decoder parameter handling to understand how to support separate beam width and length penalty per decoder. Check linked issues and PRs for any prior discussion or partial implementations.