计算机科学
变压器
解码方法
软判决解码器
人工智能
编码器
模式识别(心理学)
解析
语音识别
计算机硬件
算法
卷积神经网络
电气工程
电压
操作系统
工程类
作者
Haisong Ding,Kai Chen,Qiang Huo
标识
DOI:10.1007/978-3-030-86331-9_39
摘要
Encoder-decoder framework with attention mechanism has become a mainstream solution to handwritten mathematical expression recognition (HMER) since "watch, attend and parse (WAP)" approach was proposed in 2017, where a convolutional neural network is used as encoder and a gated recurrent unit with attention is used in decoder. Inspired by the recent success of Transformer in many applications, in this paper, we adopt the design of multi-head attention and stacked decoder in Transformer to improve the decoder part of the WAP framework for HMER. Experimental results on CROHME tasks show that multi-head attention can boost the expression recognition rate (ExpRate) of WAP from 54.32%/58.05% to 56.76%/59.72% and stacked decoder can further improve ExpRate to 57.72%/61.38% on CROHME 2016/2019 test sets.
科研通智能强力驱动
Strongly Powered by AbleSci AI