知识卡片
领域适配需比较覆盖与样本质量
领域语料可使专业词和特殊用法更贴近业务,通用预训练则可能提供更广覆盖。重新训练或继续训练是否收益,应检查语料规模、覆盖、分布和下游质量;不能只因同一行业就保证比通用向量准确。
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
In some cases, you may want to create your own domain-specific word vector models. Doing so can improve the accuracy of your model if your NLP pipeline is processing documents that use words in a way that you wouldn’t find on Google News before 2006, when Mikolov trained the reference Word2Vec model. Keep in mind, you need a lot of documents to do this as
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:摘录中关于领域适配需比较覆盖与样本质量的定义、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:In some cases, you may want to create your own domain-specific word vector models. Doing so can improve the accuracy of your model if your NLP pipeline is processing documents that use words in a way that you wouldn’t find on Google News before 2006, when Mikolov trained the reference Word2Vec model. Keep in mind, you need a lot of documents to do this as