In natural language generation, word ordering is the task of putting the words composing the output surface form in the correct grammatical order. In this paper, we propose to apply general learning-to-rank algorithms to the task of word ordering in the broader context of surface realization. The major contributions of this paper are: (i) the design of three deep neural architectures implementing pointwise, pairwise, and listwise approaches for ranking; (ii) the testing of these neural architectures on a surface realization benchmark in five natural languages belonging to different typological families. The results of our experiments show promising results, in particular highlighting the performance of the pairwise approach, paving the way for a more transparent surface realization from arbitrary tree- and graph-like structures.

Ranking Algorithms for Word Ordering in Surface Realization

Mazzei Alessandro
First
;
Cerrato Mattia;Esposito Roberto;Basile Valerio
2021-01-01

Abstract

In natural language generation, word ordering is the task of putting the words composing the output surface form in the correct grammatical order. In this paper, we propose to apply general learning-to-rank algorithms to the task of word ordering in the broader context of surface realization. The major contributions of this paper are: (i) the design of three deep neural architectures implementing pointwise, pairwise, and listwise approaches for ranking; (ii) the testing of these neural architectures on a surface realization benchmark in five natural languages belonging to different typological families. The results of our experiments show promising results, in particular highlighting the performance of the pairwise approach, paving the way for a more transparent surface realization from arbitrary tree- and graph-like structures.
2021
12
8
1
17
https://www.mdpi.com/2078-2489/12/8/337
Mazzei Alessandro, Cerrato Mattia, Esposito Roberto, Basile Valerio
File in questo prodotto:
File Dimensione Formato  
information-12-00337.pdf

Accesso aperto

Tipo di file: PDF EDITORIALE
Dimensione 411.47 kB
Formato Adobe PDF
411.47 kB Adobe PDF Visualizza/Apri

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/2318/1798667
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact