Translate, then Parse! A strong baseline for Cross-Lingual AMR Parsing

TL;DR

This paper demonstrates that a simple translate-then-parse baseline, enhanced with strong neural translation and parsing systems, outperforms recent state-of-the-art models in cross-lingual AMR parsing across multiple languages.

Contribution

The paper revisits and strengthens the simple translate+parse baseline, showing it surpasses complex models in cross-lingual AMR parsing tasks.

Findings

Translate+parse outperforms recent state-of-the-art systems

Significant Smatch score improvements across multiple languages

Strong neural models enhance baseline effectiveness

Abstract

In cross-lingual Abstract Meaning Representation (AMR) parsing, researchers develop models that project sentences from various languages onto their AMRs to capture their essential semantic structures: given a sentence in any language, we aim to capture its core semantic content through concepts connected by manifold types of semantic relations. Methods typically leverage large silver training data to learn a single model that is able to project non-English sentences to AMRs. However, we find that a simple baseline tends to be over-looked: translating the sentences to English and projecting their AMR with a monolingual AMR parser (translate+parse,T+P). In this paper, we revisit this simple two-step base-line, and enhance it with a strong NMT system and a strong AMR parser. Our experiments show that T+P outperforms a recent state-of-the-art system across all tested languages: German, Italian, Spanish and Mandarin with +14.6, +12.6, +14.3 and +16.0 Smatch points.