Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing

TL;DR

This paper proposes a cross-lingual AMR parsing approach that leverages bilingual input and an auxiliary English prediction task, significantly improving concept prediction accuracy across languages.

Contribution

It introduces bilingual input and an auxiliary task to enhance cross-lingual AMR parsing, achieving a new state-of-the-art performance.

Findings

Surpasses previous state-of-the-art by 10.6 Smatch F1 points.

Bilingual input and auxiliary tasks improve concept prediction accuracy.

Ablation study confirms effectiveness of proposed modules.

Abstract

Abstract Meaning Representation (AMR) is a rooted, labeled, acyclic graph representing the semantics of natural language. As previous works show, although AMR is designed for English at first, it can also represent semantics in other languages. However, they find that concepts in their predicted AMR graphs are less specific. We argue that the misprediction of concepts is due to the high relevance between English tokens and AMR concepts. In this work, we introduce bilingual input, namely the translated texts as well as non-English texts, in order to enable the model to predict more accurate concepts. Besides, we also introduce an auxiliary task, requiring the decoder to predict the English sequences at the same time. The auxiliary task can help the decoder understand what exactly the corresponding English tokens are. Our proposed cross-lingual AMR parser surpasses previous state-of-the-art parser by 10.6 points on Smatch F1 score. The ablation study also demonstrates the efficacy of our proposed modules.