Decoding Methods in Neural Language Generation: A Survey

Zarrieß S, Voigt H, Schüz S (2021)
Information 12(9): 355.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
OA 1.01 MB
Abstract / Bemerkung
Neural encoder-decoder models for language generation can be trained to predict words directly from linguistic or non-linguistic inputs. When generating with these so-called end-to-end models, however, the NLG system needs an additional decoding procedure that determines the output sequence, given the infinite search space over potential sequences that could be generated with the given vocabulary. This survey paper provides an overview of the different ways of implementing decoding on top of neural network-based generation models. Research into decoding has become a real trend in the area of neural language generation, and numerous recent papers have shown that the choice of decoding method has a considerable impact on the quality and various linguistic properties of the generation output of a neural NLG system. This survey aims to contribute to a more systematic understanding of decoding methods across different areas of neural NLG. We group the reviewed methods with respect to the broad type of objective that they optimize in the generation of the sequence—likelihood, diversity, and task-specific linguistic constraints or goals—and discuss their respective strengths and weaknesses.
Stichworte
neural language generation; decoding; beam search; sampling; diversity
Erscheinungsjahr
2021
Zeitschriftentitel
Information
Band
12
Ausgabe
9
Art.-Nr.
355
eISSN
2078-2489
Finanzierungs-Informationen
Open-Access-Publikationskosten wurden durch die Universität Bielefeld gefördert.
Page URI
https://pub.uni-bielefeld.de/record/2957091

Zitieren

Zarrieß S, Voigt H, Schüz S. Decoding Methods in Neural Language Generation: A Survey. Information. 2021;12(9): 355.
Zarrieß, S., Voigt, H., & Schüz, S. (2021). Decoding Methods in Neural Language Generation: A Survey. Information, 12(9), 355. https://doi.org/10.3390/info12090355
Zarrieß, S., Voigt, H., and Schüz, S. (2021). Decoding Methods in Neural Language Generation: A Survey. Information 12:355.
Zarrieß, S., Voigt, H., & Schüz, S., 2021. Decoding Methods in Neural Language Generation: A Survey. Information, 12(9): 355.
S. Zarrieß, H. Voigt, and S. Schüz, “Decoding Methods in Neural Language Generation: A Survey”, Information, vol. 12, 2021, : 355.
Zarrieß, S., Voigt, H., Schüz, S.: Decoding Methods in Neural Language Generation: A Survey. Information. 12, : 355 (2021).
Zarrieß, Sina, Voigt, Henrik, and Schüz, Simeon. “Decoding Methods in Neural Language Generation: A Survey”. Information 12.9 (2021): 355.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung 4.0 International Public License (CC-BY 4.0):
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2021-08-31T06:06:06Z
MD5 Prüfsumme
265a240812491da451c8441f51e4deeb

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar