《Denoising Distantly Supervised Open-Domain Question Answering》浅析

前言:

小编所写博客主要目的是记录之用,不免显得琐碎唠叨,不过分享出来如果能有只言片语帮到大家也是极好的。若您觉得一无所获,请及早退出,若有想法进一步交流,可评论。(原谅我没有时间排版)

论文题目:远距离监督开放问答的降噪。

1.论文提出一种新模,包括一个可以去除噪音文章的选择器,和一个从文中找出正确答案的reader。那么重点就在这个选择器怎么实现。

2.这幅图可以很好地解释这篇文章的创新点:

相比于之前的文章,作者的切入点是:之前确实有文章做过降噪处理,但是他们没有从源头做起,具体来说就是依靠于改进reader来提取正确答案,达到更好的效果。但是作者从源头做起,在第一步得到几篇文章以后,先做一个select,去除那些跟问题实际上没有关系的文章,这样第二步reader的效果就会更好。

3.下面我们关键来看如何去噪(方法):

question q =(q1, q2, · · · , q|q|)

 m paragraphs which are defined as P = {p1, p2, · · · , pm }

where pi = (p1i,p2i,· · · , p|pi |i)

我们的目标就是在给定的文章集合P,和问题q的情况下,答案a的概率。

(1)文章选择器的目标函数: Pr(pi |q, P),在给定P和q的情况下计算每篇文章的概率

(2)reader函数: Pr(a|q, pi),用LSTM实现,根据概率公式

段落编码:

把段落的每一个词都转换成向量,然后扔到某个神经网络中去,比如RNN,然后得到得到他们的隐藏状态,这个隐藏状态中包含了这个词以及周围的词的语法信息(虽然我也不知道为什么这么说)

然后用类似的方法编码问题,其中用到了attention,不过不难,只是增加了权重信息而已。大概如下:

最后只需要这个公式就可以得到我们之前提到的目标函数:

之后的具体细节小编先留着,等有必要再继续研读。

总之,本文的核心思想就是加入了select这个步骤。

未完待续···

Image denoising is the process of removing noise from an image while preserving its important features. One popular method for image denoising is non-local means (NLM), which is based on the idea that similar patches in an image have similar signal characteristics. NLM works by averaging the pixel values of similar patches in the image, thus reducing the noise without affecting the image structure. Another popular method for image denoising is wavelet shrinkage, which is based on the concept of wavelet transform. Wavelet transform decomposes an image into multi-resolution subbands, each of which captures different frequency components of the image. Wavelet shrinkage works by thresholding the wavelet coefficients in the high-frequency subbands, thus reducing the noise while preserving the image details. Combining NLM and wavelet shrinkage can improve the performance of image denoising. The NLM method can effectively remove the noise in the low-frequency subbands of the image, while the wavelet shrinkage method can remove the noise in the high-frequency subbands. The combination of these two methods can lead to a significant improvement in image denoising performance, especially for images with complex and heterogeneous noise patterns. In summary, image denoising using non-local means and wavelet shrinkage is a powerful technique for removing noise from images while preserving their important features. This method can be used in a variety of applications, including medical imaging, remote sensing, and image processing.
评论 3
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值
>