Papers › Incorporating Graph Information in Transformer-based AMR Parsing

Incorporating Graph Information in Transformer-based AMR Parsing

23 Jun 2023arXiv:2306.13467archive 2025-07-28

Pavlo Vasylenko, Pere-Lluís Huguet Cabot, Abelardo Carlos Martínez Lorenzo, Roberto Navigli

Abstract Meaning Representation (AMR) is a Semantic Parsing formalism that aims at providing a semantic graph abstraction representing a given text. Current approaches are based on autoregressive language models such as BART or T5, fine-tuned through Teacher Forcing to obtain a linearized version of the AMR graph from a sentence. In this paper, we present LeakDistill, a model and method that explores a modification to the Transformer architecture, using structural adapters to explicitly incorporate graph information into the learned representations and improve AMR parsing performance. Our experiments show how, by employing word-to-node alignment to embed graph structural information into the encoder at training time, we can obtain state-of-the-art AMR parsing through self-knowledge distillation, even without the use of additional data. We release the code at \url{http://www.github.com/sapienzanlp/LeakDistill}.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sapienzanlp/leakdistill officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AMR ParsingAbstract Meaning RepresentationKnowledge DistillationSelf-Knowledge DistillationSemantic ParsingSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
AMR Parsing LDC2017T10 LeakDistill Smatch 86.1 #3 of 27 Archive leaderboard report
AMR Parsing LDC2017T10 LeakDistill (base) Smatch 84.7 #10 of 27 Archive leaderboard report
AMR Parsing LDC2020T02 LeakDistill Smatch 84.6 #3 of 13 Archive leaderboard report
AMR Parsing LDC2020T02 LeakDistill (base) Smatch 83.5 #10 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdafactorAdamAttentionAttention DropoutBARTBPEDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSentencePieceSoftmaxT5Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections