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

Meaning Representation (AMR) is a Semantic Parsing formalism thataims at providing a semantic graph abstraction representing a given text.Current approaches are based on autoregressive language models such as BART orT5, fine-tuned through Teacher Forcing to obtain a linearized version of theAMR graph from a sentence. In this paper, we present LeakDistill, a model andmethod that explores a modification to the Transformer architecture, usingstructural adapters to explicitly incorporate graph information into thelearned representations and improve AMR parsing performance. Our experimentsshow how, by employing word-to-node alignment to embed graph structuralinformation into the encoder at training time, we can obtain state-of-the-artAMR parsing through self-knowledge distillation, even without the use ofadditional data. We release the code at\url{http://www.github.com/sapienzanlp/LeakDistill}.

Incorporating Graph Information in Transformer-based AMR Parsing