BriefGPT.xyz
Sep, 2022
中文AMR解析的两阶段方法
A Two-Stage Method for Chinese AMR Parsing
HTML
PDF
Liang Chen, Bofei Gao, Baobao Chang
TL;DR
本文提出了一种两阶段方法进行中文AMR分析和对齐生成的模型，分别为概念预测和关系预测阶段，模型在CAMR 2.0测试集和CAMRP-2022盲测试集上分别取得了0.7756和0.7074的Align-Smatch F1分数，同时分析了误差传播和类别不平衡问题的限制。
Abstract
In this paper, we provide a detailed description of our system at CAMRP-2022 evaluation. We firstly propose a
two-stage method
to conduct
chinese amr parsing
with
→