Cross-domain Generalization for AMR Parsing
Bai, Xuefeng, Yang, Seng, Cui, Leyang, Song, Linfeng, Zhang, Yue
–arXiv.org Artificial Intelligence
Abstract Meaning Representation (AMR) parsing aims to predict an AMR graph from textual input. Recently, there has been notable growth in AMR parsing performance. However, most existing work focuses on improving the performance in the specific domain, ignoring the potential domain dependence of AMR parsing systems. To address this, we extensively evaluate five representative AMR parsers on five domains and analyze challenges to cross-domain AMR parsing. We observe that challenges to cross-domain AMR parsing mainly arise from the distribution shift of words and AMR concepts. Based on our observation, we investigate two approaches to reduce the domain distribution divergence of text and AMR features, respectively. Experimental results on two out-of-domain test sets show the superiority of our method.
arXiv.org Artificial Intelligence
Oct-22-2022
- Country:
- Oceania > Australia
- North America
- Dominican Republic (0.04)
- United States
- Maryland > Baltimore (0.04)
- Washington > King County
- New York > New York County
- New York City (0.04)
- New Mexico > Santa Fe County
- Santa Fe (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Colorado > Denver County
- Denver (0.04)
- California > San Diego County
- San Diego (0.04)
- Canada > British Columbia
- Europe
- Germany > Berlin (0.04)
- Slovenia (0.04)
- Latvia > Riga Municipality
- Riga (0.04)
- Italy > Tuscany
- Florence (0.04)
- France > Provence-Alpes-Côte d'Azur
- Bouches-du-Rhône > Marseille (0.04)
- Spain
- Valencian Community > Valencia Province
- Valencia (0.04)
- Catalonia > Barcelona Province
- Barcelona (0.04)
- Valencian Community > Valencia Province
- Denmark > Capital Region
- Copenhagen (0.04)
- Bulgaria > Sofia City Province
- Sofia (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia > China
- Hong Kong (0.05)
- Guangdong Province > Shenzhen (0.04)
- Genre:
- Research Report
- New Finding (0.68)
- Experimental Study (0.46)
- Research Report
- Technology: