知识卡片
符号嵌入依赖出现环境和粒度
课程编号或其他符号若在有规律的上下文出现,也可学习分布表示;带内部结构时可选择更小片段。学得相似并不代表解出编号全部含义,更不能把任意密码都称可用Word2Vec自动破解;需说明可观察结构与验证目标。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 用词嵌入推理
原书出处 · 1 处
- · 查看原书依据
Word embeddings, such as Word2Vec, are useful not only for English words but also for any sequence of symbols where the sequence and proximity of symbols is representative of their meaning. If your symbols have semantics, embeddings may be useful.
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第06章《用词嵌入推理》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-6.html)
- 结论依据:摘录中关于符号嵌入依赖出现环境和粒度的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:Word embeddings, such as Word2Vec, are useful not only for English words but also for any sequence of symbols where the sequence and proximity of symbols is representative of their meaning. If your symbols have semantics, embeddings may be useful.