JN_rainbow的博客

本文是对Google2017年发表于NIPS上的论文"Attention is all you need"的阅读笔记. 对于深度学习中NLP问题，通常是将句子分词后，转化词向量序列，转为seq2seq问题. RNN方案 采用RNN模型，通常是递归地进行yt=f(yt−1,xt)y_t=f(y_{t-1},x_t)yt​=f(yt−1​,xt​)，优点在于结构简单，十分适合序列建模；缺点在于需要...

This is a paper about relationship extraction on NAACL 2019. Connecting language and knowledge with heterogeneous representations for neural relation extraction Problem In the process of building a kn...