![](https://img-blog.csdnimg.cn/20201014180756925.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
NLP
文章平均质量分 96
LinMoson
这个作者很懒,什么都没留下…
展开
-
Stanford NLP4
Lesson 18 我们想要理解meaning of larger phrases,比如snowboarder=person on a snowboard 人类理解的方式是:理解每个components meaning,然后将它们组合起来 interpret the meaning of larger text units - entities,descriptive terms,facts,arguments,stories - by semantic composition of small eleme原创 2021-02-23 20:08:36 · 577 阅读 · 0 评论 -
Stanford NLP3
Lesson 13 Representation for a word 早年间,supervised neural network,效果还不如一些feature classifier(SVM之类的) 后来训练unsupervised neural network,效果赶上feature classifier了,但是花费的时间很长(7weeks) 如果再加一点hand-crafted features,准确率还能进一步提升 后来,我们可以train on supervised small corpus,找到d原创 2021-02-23 20:07:55 · 579 阅读 · 0 评论 -
Stanford NLP2
Lesson 7:Neural Machine Translation 根据chain rule,如果前三个都很小,gradient vanish Consider the gradient of the loss J(i)(θ)J^{(i)}(\theta)J(i)(θ) on step i,with respect to the hidden state h(j)h^{(j)}h(j) at step j ∂J(i)(θ)∂h(j)=∂J(i)(θ)∂h(i)∏j≤t≤i∂h(t)(θ)∂h(t−1)原创 2021-02-23 20:06:52 · 313 阅读 · 0 评论