EMNLP Findings2020
The Role of Reentrancies in Abstract Meaning Representation Parsing
Marco Damonte, Ida Szubert, Shay B. Cohen, Mark Steedman
Abstract
Meaning Representation (AMR) parsing aims at converting sentences into AMR representations. These are graphs and not trees because AMR supports reentrancies (nodes with more than one parent). Following previous findings on the importance of reentrancies for AMR, we empirically find and discuss several linguistic phenomena responsible for reentrancies in AMR, some of which have not received attention before. We categorize the types of errors AMR parsers make with respect to reentrancies. Furthermore, we find that correcting these errors provides an increase of up to 5% Smatch in parsing performance and 20% in reentrancy prediction.
Ask Lune
Ask anything. The answer quotes the paper.
Lune reads all of it and the papers around it, then shows you the passages behind every answer.
Lune answers from
the full paper · 8 top-tier papers that cite it · related work
Free to start. No credit card required.
Cited by top-tier papers8
- Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text GenerationYan Zhang, Zhijiang Guo, Zhiyang Teng, Wei Lu et al.EMNLP 2020 · 16 citations
- A Differentiable Relaxation of Graph Segmentation and Alignment for AMR ParsingChunchuan Lyu, Shay B. Cohen, Ivan TitovEMNLP 2021 · 13 citations
- AMR Parsing is Far from Solved: GrAPES, the Granular AMR Parsing Evaluation SuiteJonas Groschwitz, Shay B. Cohen, Lucia Donatelli, Meaghan FowlieEMNLP 2023 · 5 citations
- Structural Adapters in Pretrained Language Models for AMR-to-Text GenerationLeonardo F. R. Ribeiro, Yue Zhang, Iryna GurevychEMNLP 2021
- XLPT-AMR: Cross-Lingual Pre-Training via Multi-Task Learning for Zero-Shot AMR Parsing and Text GenerationDongqin Xu, Junhui Li, Muhua Zhu, Min Zhang et al.ACL 2021
Builds on1
Related papers
- Making Better Use of Bilingual Information for Cross-Lingual AMR ParsingYitao Cai, Zhe Lin, Xiaojun WanACL Findings 2021 · 3 citations
- Cross-domain Generalization for AMR ParsingXuefeng Bai, Sen Yang, Leyang Cui, Linfeng Song et al.EMNLP 2022 · 1 citation
- Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR AlignmentsAustin Blodgett, Nathan SchneiderACL 2021
- Guiding AMR Parsing with Reverse Graph LinearizationBofei Gao, Liang Chen, Peiyi Wang, Zhifang Sui et al.EMNLP Findings 2023
- XL-AMR: Enabling Cross-Lingual AMR Parsing with Transfer Learning TechniquesRexhina Blloshmi, Rocco Tripodi, Roberto NavigliEMNLP 2020 · 48 citations
