In Text-to-AMR parsing, current state-of-the-art semantic parsers use cumbersome pipelines integrating several different modules or components, and exploit graph recategorization, i.e., a set of content-specific heuristics that are developed on the basis of the training set. However, the generalizability of graph recategorization in an out-of-distribution setting is unclear. In contrast, state-of-the-art AMR-to-Text generation, which can be seen as the inverse to parsing, is based on simpler seq2seq. In this paper, we cast Text-to-AMR and AMR-to-Text as a symmetric transduction task and show that by devising a careful graph linearization and extending a pretrained encoder-decoder model, it is possible to obtain state-of-the-art performances in both tasks using the very same seq2seq approach, i.e., SPRING (Symmetric PaRsIng aNd Generation). Our model does not require complex pipelines, nor heuristics built on heavy assumptions. In fact, we drop the need for graph recategorization, showing that this technique is actually harmful outside of the standard benchmark. Finally, we outperform the previous state of the art on the English AMR 2.0 dataset by a large margin: on Text-to-AMR we obtain an improvement of 3.6 Smatch points, while on AMR-to-Text we outperform the state of the art by 11.2 BLEU points. We release the software at github.com/SapienzaNLP/spring.

One SPRING to Rule Them Both: Symmetric AMR Semantic Parsing and Generation without a Complex Pipeline / Bevilacqua, Michele; Blloshmi, Rexhina; Navigli, Roberto. - 35:14(2021), pp. 12564-12573. ((Intervento presentato al convegno Thirty-Fifth AAAI Conference on Artificial Intelligence tenutosi a Online.

One SPRING to Rule Them Both: Symmetric AMR Semantic Parsing and Generation without a Complex Pipeline

Michele Bevilacqua
Primo
;
Rexhina Blloshmi
Secondo
;
Roberto Navigli
Ultimo
2021

Abstract

In Text-to-AMR parsing, current state-of-the-art semantic parsers use cumbersome pipelines integrating several different modules or components, and exploit graph recategorization, i.e., a set of content-specific heuristics that are developed on the basis of the training set. However, the generalizability of graph recategorization in an out-of-distribution setting is unclear. In contrast, state-of-the-art AMR-to-Text generation, which can be seen as the inverse to parsing, is based on simpler seq2seq. In this paper, we cast Text-to-AMR and AMR-to-Text as a symmetric transduction task and show that by devising a careful graph linearization and extending a pretrained encoder-decoder model, it is possible to obtain state-of-the-art performances in both tasks using the very same seq2seq approach, i.e., SPRING (Symmetric PaRsIng aNd Generation). Our model does not require complex pipelines, nor heuristics built on heavy assumptions. In fact, we drop the need for graph recategorization, showing that this technique is actually harmful outside of the standard benchmark. Finally, we outperform the previous state of the art on the English AMR 2.0 dataset by a large margin: on Text-to-AMR we obtain an improvement of 3.6 Smatch points, while on AMR-to-Text we outperform the state of the art by 11.2 BLEU points. We release the software at github.com/SapienzaNLP/spring.
978-1-57735-866-4
File allegati a questo prodotto
File Dimensione Formato  
Bevilacqua_One-SPRING_2021.pdf

solo gestori archivio

Note: articolo principale
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 286.15 kB
Formato Adobe PDF
286.15 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Bevilacqua_Postprint_One-SPRING_2021.pdf

accesso aperto

Note: https://ojs.aaai.org/index.php/AAAI/article/view/17489
Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 5.09 MB
Formato Adobe PDF
5.09 MB Adobe PDF Visualizza/Apri PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11573/1550785
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 21
  • ???jsp.display-item.citation.isi??? 8
social impact