piskvorky/gensim

potential Doc2Vec feature: reverse inference, to synthesize doc/summary words

Open

#2,459 建立於 2019年4月21日

在 GitHub 查看
 (5 留言) (0 反應) (0 負責人)Python (15,144 star) (4,349 fork)batch import
Hacktoberfestdifficulty mediumfeaturegood first issuewishlist

描述

Motivated by the SO question: https://stackoverflow.com/questions/55768598/interpret-the-doc2vec-vectors-clusters-representation/55779049#55779049

Doc2Vec could plausibly have a function that's reverse-inference: take a doc-vector, return a (ranked) list of words most-predicted by that input vector. It'd work highly analogously to Word2Vec.predict_output_word(). Such a list of words might be useful as a sort-of summary or label for a doc-vector.

貢獻者指南

技術棧
python
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。
3
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
Pythongensim basicsWord2Vec.predict output word method
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。
40
研究方向
The issue requests a reverse inference method for Doc2Vec, analogous to Word2Vec's predict output word. Start by examining the source code for predict output word in gensim's Word2Vec implementation, then adapt it for Doc2Vec using the doc vector as input. The issue comments and the linked StackOverflow question may provide additional context and usage examples. Ensure the implementation returns a ranked list of words most likely predicted by a given doc vector.