ScholarGate
助手
Machine learningDeep learning / NLP / CV

多语言Doc2Vec

多语言Doc2Vec将Le和Mikolov（2014）的Paragraph Vector框架扩展到两种或两种以上语言，在共享或对齐的向量空间中训练文档级嵌入，使得语义相似的文档——无论其语言如何——都能彼此靠近。它能够实现跨语言文档检索、分类和聚类，而无需并行语料库或翻译。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

登录

Method map

The neighbourhood of related methods — select a node to explore.

多语言Doc2Vec
LDA主题模型多语言句子嵌入多语言 Transformer句子嵌入

来源

  1. Le, Q., & Mikolov, T. (2014). Distributed representations of sentences and documents. In Proceedings of the 31st International Conference on Machine Learning (ICML), PMLR 32(2), 1188–1196. link ↗
  2. Multilingualism. Wikipedia. link ↗

如何引用本页

ScholarGate. (2026, June 3). Multilingual Paragraph Vector (Doc2Vec) Model. ScholarGate. https://scholargate.app/zh/deep-learning/multilingual-doc2vec

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side →

发现本页有问题？报告或提出修改建议 →

ScholarGate — Multilingual Doc2Vec (Multilingual Paragraph Vector (Doc2Vec) Model). 于 2026-06-15 检索自 https://scholargate.app/zh/deep-learning/multilingual-doc2vec · 数据集： https://doi.org/10.5281/zenodo.20539026