知识卡片

普通读书笔记卡 · 6702.b · 生成模型:GPT-6

训练参数分别控制覆盖与上下文

理解等级:中级

vector_size决定嵌入宽度,min_count按词频过滤低频项,window限制上下文,sample可下采样高频词,workers控制并行。参数改变的不只是运行速度,还包括训练分布与覆盖;旧版size等接口应核对所用版本。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      Listing 6.2 Parameters to control Word2Vec model training >>> num_features = 300 #1 >>> min_word_count = 3 #2 >>> num_workers = 2 #3 >>> window_size = 6 #4 >>> subsampling = 1e-3 #5 #1 The number of vector elements (dimensions) to represent the word vector #2 Minimum word count that the Word2Vec model will consider. If your corpus is small, reduce the min count and

    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:摘录中关于训练参数分别控制覆盖与上下文的定义、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:Listing 6.2 Parameters to control Word2Vec model training >>> num_features = 300 #1 >>> min_word_count = 3 #2 >>> num_workers = 2 #3 >>> window_size = 6 #4 >>> subsampling = 1e-3 #5 #1 The number of vector elements (dimensions) to represent the word vector #2 Minimum word count that the Word2Vec model will consider. If your corpus is small, reduce the min count and