Incorporating Graph Information in Transformer-based AMR Parsing
Abstract
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}.
- Publication:
-
arXiv e-prints
- Pub Date:
- June 2023
- DOI:
- 10.48550/arXiv.2306.13467
- arXiv:
- arXiv:2306.13467
- Bibcode:
- 2023arXiv230613467V
- Keywords:
-
- Computer Science - Computation and Language;
- Computer Science - Artificial Intelligence
- E-Print:
- ACL 2023. Please cite authors correctly using both lastnames ("Mart\'inez Lorenzo", "Huguet Cabot")