English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Text generation from Abstract Meaning Representation (AMR) has substantiallybenefited from the popularized Pretrained Language Models (PLMs). Myriadapproaches have linearized the input graph as a sequence of tokens to fit thePLM tokenization requirements. Nevertheless, this transformation jeopardizesthe structural integrity of the graph and is therefore detrimental to itsresulting representation. To overcome this issue, Ribeiro et al. have recentlyproposed StructAdapt, a structure-aware adapter which injects the input graphconnectivity within PLMs using Graph Neural Networks (GNNs). In this paper, weinvestigate the influence of Relative Position Embeddings (RPE) on AMR-to-Text,and, in parallel, we examine the robustness of StructAdapt. Through ablationstudies, graph attack and link prediction, we reveal that RPE might bepartially encoding input graphs. We suggest further research regarding the roleof RPE will provide valuable insights for Graph-to-Text generation.

Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters