Skip-Thought Vectors

  • 类型:arxiv
  • 标识:1506.06726
  • 链接:https://arxiv.org/abs/1506.06726
  • 主题:multimodal
  • 主分类:llm-infra
  • 形态:method
  • 被引:2488
  • 被引来源:Semantic Scholar
  • S2被引:2488
  • OpenAlex被引:723
  • 影响力被引:266
  • TLDR:The approach for unsupervised learning of a generic, distributed sentence encoder is described, using the continuity of text from books to train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage.
  • OpenAlex ID:W1486649854
  • OpenAlex DOI:10.48550/arxiv.1506.06726
  • DOI:10.48550/arxiv.1506.06726
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/1506.06726
  • OpenAlex更新:2026-08-23
  • 待LLM分类:否
  • 成熟度:research
  • 场景:sentence embeddings、unsupervised learning、representation
  • 标题中文:Skip-Thought Vectors
  • TLDR中文:描述了一种无监督学习通用分布式句子编码器的方法,利用书籍文本的连续性,训练编码器-解码器模型以重建编码段落的周围句子。
  • 来源文件
  • [OpenAlex discover]
  • [S2 enrich]