Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters
Sebastien Montella, Alexis Nasr, Johannes Heinecke, Frederic Bechet, Lina M. Rojas Barahona
Abstract
Text generation from Abstract Meaning Representation (AMR) has substantially benefited from the popularized Pretrained Language Models (PLMs). Myriad approaches have linearized the input graph as a sequence of tokens to fit the PLM tokenization requirements. Nevertheless, this transformation jeopardizes the structural integrity of the graph and is therefore detrimental to its resulting representation. To overcome this issue, Ribeiro et al. (2021b) have recently proposed StructAdapt, a structure-aware adapter which injects the input graph connectivity within PLMs using Graph Neural Networks (GNNs). In this paper, we investigate the influence of Relative Position Embeddings (RPE) on AMR-to-Text, and, in parallel, we examine the robustness of StructAdapt. Through ablation studies, graph attack and link prediction, we reveal that RPE might be partially encoding input graphs. We suggest further research regarding the role of RPE will provide valuable insights for Graph-to-Text generation.- Anthology ID:
- 2023.eacl-main.51
- Volume:
- Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 727–736
- Language:
- URL:
- https://aclanthology.org/2023.eacl-main.51
- DOI:
- 10.18653/v1/2023.eacl-main.51
- Cite (ACL):
- Sebastien Montella, Alexis Nasr, Johannes Heinecke, Frederic Bechet, and Lina M. Rojas Barahona. 2023. Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 727–736, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters (Montella et al., EACL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2023.eacl-main.51.pdf