Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR Parsing

TL;DR

This paper empirically assesses the effectiveness of meta-learning versus joint learning for cross-lingual AMR parsing across multiple languages, including newly developed test sets for Korean and Croatian.

Contribution

It introduces a meta-learning approach for cross-lingual AMR parsing and compares it with classical joint learning across various low-resource scenarios.

Findings

Meta-learning slightly outperforms joint learning in 0-shot scenarios.

Performance gains diminish as the number of training examples increases.

Korean and Croatian test sets are newly developed and publicly released.

Abstract

Cross-lingual AMR parsing is the task of predicting AMR graphs in a target language when training data is available only in a source language. Due to the small size of AMR training data and evaluation data, cross-lingual AMR parsing has only been explored in a small set of languages such as English, Spanish, German, Chinese, and Italian. Taking inspiration from Langedijk et al. (2022), who apply meta-learning to tackle cross-lingual syntactic parsing, we investigate the use of meta-learning for cross-lingual AMR parsing. We evaluate our models in $k$-shot scenarios (including 0-shot) and assess their effectiveness in Croatian, Farsi, Korean, Chinese, and French. Notably, Korean and Croatian test sets are developed as part of our work, based on the existing The Little Prince English AMR corpus, and made publicly available. We empirically study our method by comparing it to classical joint learning. Our findings suggest that while the meta-learning model performs slightly better in 0-shot evaluation for certain languages, the performance gain is minimal or absent when $k$ is higher than 0.