IntroductionThis paper is going to show that a discrimininatively trained, multi-layer capsule system achieves state-of-the-art performance on MNIST and isconsiderably better than a convolutional net
编码问题之前听说python 3.6极其的好，在编码上面都是UTF-8的，这样可以解决很多自然语言处理中的常见编码问题。事实证明还是会有编码问题，只是解决的方法不像python 2.7那样感觉有点dirty。 以下是python 2.7的环境下解决编码问题的方法123import sysreload(sys)sys.setdefaultencoding('UTF-8') 但是我在使用“高大上”的p
今天发现打开腾讯NBA和斗鱼的时候，页面非常卡，而且打开Activity Monitor之后，发现Safari里的Flash插件经常CPU 100%，并且会出现未响应。 上网看到一个方法是或者自己手动把 RTMFPP2PDisable=1 这行添加到 /Library/Application\ Support/Macromedia/mms.cfg 这个里面去都可以。 在新 osx 系统里面， sa
A dependency measure based on Jensen-ShannonThey define a dependency measure between two random variables, which is based on the Jensen-Shannon divergence. The Kullback-Leibler (KL) divergence of a d
MethologyHowNetHowNet annotates precise senses to each word, and for each sense, HowNet annotates the significance of parts and attributes represented by sememes.
AbstractThey introduce an extension to the bag-of-words model for learning words represen- tations that take into account both syntactic and semantic properties within language. IntroductionFor BOW an
AbstractContext representations are a key element in distributional models of word meaning. A recently proposed approach suggests to represent a context of a target word by a substitute vector. In thi
IntroductionMost existing work on multi-task learning attempts to divide the features of different tasks into private and shared spaces, merely based on whether parameters of some components should be
IntroductionDiscourse structure represents the organization of a text as a tree. Experimental results show that variants of our model outperform prior work on four out of five tasks considered. In thi