A Two-Stage Method for Chinese AMR Parsing

TL;DR

This paper introduces a two-stage Chinese AMR parsing method with alignment generation, achieving high F1 scores and providing analysis of limitations like error propagation and class imbalance.

Contribution

The paper presents a novel two-stage approach for Chinese AMR parsing that improves alignment accuracy and offers insights into current limitations.

Findings

Achieved 0.7756 and 0.7074 Align-Smatch F1 scores on test sets.

Identified limitations such as error propagation and class imbalance.

Released code and models for reproducibility.

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 alignment generation, which includes Concept-Prediction and Relation-Prediction stages. Our model achieves 0.7756 and 0.7074 Align-Smatch F1 scores on the CAMR 2.0 test set and the blind-test set of CAMRP-2022 individually. We also analyze the result and the limitation such as the error propagation and class imbalance problem we conclude in the current method. Code and the trained models are released at https://github.com/PKUnlp-icler/Two-Stage-CAMRP for reproduction.