AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing
Lorenzo, Abelardo Carlos Martínez, Cabot, Pere-Lluís Huguet, Navigli, Roberto
–arXiv.org Artificial Intelligence
In this paper, we examine the current state-of-the-art in AMR parsing, which relies on ensemble strategies by merging multiple graph predictions. Our analysis reveals that the present models often violate AMR structural constraints. To address this issue, we develop a validation method, and show how ensemble models can exploit SMATCH metric weaknesses to obtain higher scores, but sometimes result in corrupted graphs. Additionally, we highlight the demanding need to compute the SMATCH score among all possible predictions. To overcome these challenges, we propose two novel ensemble strategies based on Transformer models, improving robustness to structural constraints, while also reducing the computational time. Our methods provide new insights for enhancing AMR parsers and metrics. Our code is available at \href{https://www.github.com/babelscape/AMRs-Assemble}{github.com/babelscape/AMRs-Assemble}.
arXiv.org Artificial Intelligence
Jun-19-2023
- Country:
- South America > Chile
- North America
- Dominican Republic (0.04)
- United States
- Washington > King County
- Seattle (0.04)
- New Mexico > Santa Fe County
- Santa Fe (0.04)
- California > San Diego County
- San Diego (0.04)
- Washington > King County
- Canada > British Columbia
- Europe
- Italy (0.04)
- Sweden > Stockholm
- Stockholm (0.04)
- Spain
- Valencian Community > Valencia Province
- Valencia (0.04)
- Catalonia > Barcelona Province
- Barcelona (0.04)
- Valencian Community > Valencia Province
- Latvia > Riga Municipality
- Riga (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.05)
- Bulgaria > Sofia City Province
- Sofia (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Genre:
- Research Report (1.00)
- Technology: