| Title | Hierarchical Curriculum Learning for AMR Parsing |
| Authors | Wang, Peiyi Chen, Liang Liu, Tianyu Dai, Damai Cao, Yunbo Chang, Baobao Sui, Zhifang |
| Affiliation | Peking Univ, Key Lab Computat Linguist, MOE, Beijing, Peoples R China Tencent Cloud Xiaowei, Shenzhen, Peoples R China |
| Issue Date | 2022 |
| Publisher | PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022): (SHORT PAPERS), VOL 2 |
| Abstract | A Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, and is recently empowered by pretrained sequence-to-sequence models. However, there exists a gap between their flat training objective (i.e., equally treats all output tokens) and the hierarchical AMR structure, which limits the model generalization. To bridge this gap, we propose a Hierarchical Curriculum Learning (HCL) framework with Structure-level (SC) and Instance-level Curricula (IC). SC switches progressively from core to detail AMR semantic elements while IC transits from structure-simple to -complex AMR instances during training. Through these two warming-up processes, HCL reduces the difficulty of learning complex structures, thus the flat model can better adapt to the AMR hierarchy. Extensive experiments on AMR2.0, AMR3.0, structure-complex and out-of-distribution situations verify the effectiveness of HCL. |
| URI | http://hdl.handle.net/20.500.11897/649484 |
| ISBN | 978-1-955917-22-3 |
| Indexed | CPCI-SSH(ISSHP) CPCI-S(ISTP) |
| Appears in Collections: | 计算语言学教育部重点实验室 |
