English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this paper, we examine the current state-of-the-art in AMR parsing, whichrelies on ensemble strategies by merging multiple graph predictions. Ouranalysis reveals that the present models often violate AMR structuralconstraints. To address this issue, we develop a validation method, and showhow ensemble models can exploit SMATCH metric weaknesses to obtain higherscores, but sometimes result in corrupted graphs. Additionally, we highlightthe demanding need to compute the SMATCH score among all possible predictions.To overcome these challenges, we propose two novel ensemble strategies based onTransformer models, improving robustness to structural constraints, while alsoreducing the computational time. Our methods provide new insights for enhancingAMR parsers and metrics. Our code is available at\href{https://www.github.com/babelscape/AMRs-Assemble}{github.com/babelscape/AMRs-Assemble}.

AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing