Abstract Meaning Representation

Abstract Meaning Representation (AMR)[1][2] is a semantic representation language. AMR graphs are rooted, labeled, directed, acyclic graphs (DAGs), comprising whole sentences. They are intended to abstract away from syntactic representations, in the sense that sentences which are similar in meaning should be assigned the same AMR, even if they are not identically worded. By nature, the AMR language is biased towards English – it is not meant to function as an international auxiliary language.

Example

In this paper,[1] there are these two equivalent formats for representing the same sentence: The boy wants to go.

Logic format

AMR format

 
(w / want-01
  :arg0 (b / boy)
  :arg1 (g / go-01
    :arg0 b))

This last representation makes the will of the boy more explicit, highlighting that the intention of the boy is that he himself goes away.

gollark: What do you "need" with the motherboard, I mean.
gollark: So what do you "need"?
gollark: THEY ARE SOMEWHAT OVERPRICED!
gollark: BUY RYZEN ALTHOUGH POSSIBLY NOT AMD GPUs!
gollark: AMD FOREVER! DOWN WITH INTEL'S MOSTLY MONOPOLY!

References
  1. Banarescu, Laura; Bonial, Claire; Cai, Shu; Georgescu, Madalina; Griffitt, Kira; Hermjakob, Ulf; Knight, Kevin; Koehn, Philipp; Palmer, Martha; Schneider, Nathan (2013). Abstract Meaning Representation for Sembanking (PDF). Sofia, Bulgaria: Association for Computational Linguistics. pp. 178–186. Retrieved 28 June 2019.
  2. "Abstract Meaning Representation (AMR)".


This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.