nlp经典论文集 http://www.marekrei.com/blog/74-summaries-of-machine-learning-and-nlp-research/ prerequisite MLemail bert相比于Tr

一、Basic conceptsExample graph： 1.Nodes：represent entities2.Labels：group nodes into sets by a certain label[^one node can

一、果昔[^Tips:if you want to make juice stickier,you can add some avocado(牛油果)]: 1.avocado+apple+mint(薄荷) taste: 2.mango+p

p1.Train/dev/test sets Train：训练集，用来训练各种模型 dev：验证集(development set)/Hold-out cross validation set，评估这些模型，通过迭代选出最优模型 test：

Abstract Sememes are minimum semantic units of word meanings, and the meaning of each word sense is typically composed b

1.2数学符号 创建词表（UNK表示未知词）2.represent word(ono-hot) [^use x<1>,x<2>,…,x,tx表示sequence length]: 1.3RNN(Recurren