A language-independent representation of meaning is one of the most coveted dreams in Natural Language Understanding. With this goal in mind, several formalisms have been proposed as frameworks for meaning representation in Semantic Parsing. And yet, the dependencies these formalisms share with respect to language-specific repositories of knowledge make the objective of closing the gap between high- and low-resourced languages hard to accomplish. In this paper, we present the BabelNet Meaning Representation (BMR), an interlingual formalism that abstracts away from language-specific constraints by taking advantage of the multilingual semantic resources of BabelNet and VerbAtlas. We describe the rationale behind the creation of BMR and put forward BMR 1.0, a dataset labeled entirely according to the new formalism. Moreover, we show how BMR is able to outperform previous formalisms thanks to its fully-semantic framing, which enables top-notch multilingual parsing and generation. We release the code at https://github.com/SapienzaNLP/bmr.

Fully-Semantic Parsing and Generation: the BabelNet Meaning Representation / Martinez Lorenzo, Abelardo Carlos; Maru, Marco; Navigli, Roberto. - 1:(2022), pp. 1727-1741. (Intervento presentato al convegno Association for Computational Linguistics tenutosi a Dublin, Ireland) [10.18653/v1/2022.acl-long.121].

Fully-Semantic Parsing and Generation: the BabelNet Meaning Representation

Martinez Lorenzo, Abelardo Carlos
;
Maru, Marco
;
Navigli, Roberto
2022

Abstract

A language-independent representation of meaning is one of the most coveted dreams in Natural Language Understanding. With this goal in mind, several formalisms have been proposed as frameworks for meaning representation in Semantic Parsing. And yet, the dependencies these formalisms share with respect to language-specific repositories of knowledge make the objective of closing the gap between high- and low-resourced languages hard to accomplish. In this paper, we present the BabelNet Meaning Representation (BMR), an interlingual formalism that abstracts away from language-specific constraints by taking advantage of the multilingual semantic resources of BabelNet and VerbAtlas. We describe the rationale behind the creation of BMR and put forward BMR 1.0, a dataset labeled entirely according to the new formalism. Moreover, we show how BMR is able to outperform previous formalisms thanks to its fully-semantic framing, which enables top-notch multilingual parsing and generation. We release the code at https://github.com/SapienzaNLP/bmr.
2022
Association for Computational Linguistics
natural language processing; computational linguistics; Semantic Parsing; AMR; BMR
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Fully-Semantic Parsing and Generation: the BabelNet Meaning Representation / Martinez Lorenzo, Abelardo Carlos; Maru, Marco; Navigli, Roberto. - 1:(2022), pp. 1727-1741. (Intervento presentato al convegno Association for Computational Linguistics tenutosi a Dublin, Ireland) [10.18653/v1/2022.acl-long.121].
File allegati a questo prodotto
File Dimensione Formato  
AbelardoCarlosMartínez_Fully-Semantic_2022.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 2.36 MB
Formato Adobe PDF
2.36 MB Adobe 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: https://hdl.handle.net/11573/1656313
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 1
social impact