CCG-Supertagging-LSTM

NLP CCG Supertagging LSTM
PaperLookThroughy
Publish Date:   2020-10-20
Update Date:   2020-10-28
Word Count:   188
Read Times:   1 Min
Read Count:  

Title

《Supertagging with LSTMs》

LSTM框架

image-20201028085923409

[^LSTM中有三个门电路进行控制，门电路输出为1时门电路打开，反之关闭。]: 相比于Nerual Network,LSTM相当于外接四个电路进行输入，每次输入都对两个输入进行权值的加权运算。最后得出output

Abstract

​ In this paper we present new state-of-the-art performance on CCG supertagging and parsing.We analyze the performance of several neural models and demonstrate that while feed-forward architectures can compete with bidirectional LSTMs on POS tagging, models that encode the complete sentence are necessary for the long range syntactic information encoded in supertags.

Author: Weiruohe
Link: https://weiruohe.github.io/2020/10/20/ccg-supertagging-lstm/
Reprint policy: All articles in this blog are used except for special statements CC BY 4.0 reprint polocy. If reproduced, please indicate source Weiruohe !
NLP CCG Supertagging LSTM
赏
  TOC