Logo des Repositoriums
 
ConferencePaper

Programming in Natural Language with fuSE: Synthesizing Methods from Spoken Utterances Using Deep Natural Language Understanding

Lade...
Vorschaubild

Volltext URI

Dokumententyp

Text/ConferencePaper

Zusatzinformation

Datum

2021

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik e.V.

Zusammenfassung

With fuSE laypeople can create simple programs: one can teach intelligent systems new functions using plain English. fuSE uses deep learning to synthesize source code: it creates method signatures (for newly learned functions) and generates API calls (to form the body). In an evaluation on an unseen dataset fuSE synthesized 84.6% of the signatures and 66.9% of the API calls correctly.

Beschreibung

Weigelt, Sebastian; Steurer, Vanessa; Hey, Tobias; Tichy, Walter (2021): Programming in Natural Language with fuSE: Synthesizing Methods from Spoken Utterances Using Deep Natural Language Understanding. Software Engineering 2021. DOI: 10.18420/SE2021_46. Bonn: Gesellschaft für Informatik e.V.. PISSN: 1617-5468. ISBN: 978-3-88579-704-3. pp. 117-118. Braunschweig/Virtuell. 22.-26. Februar 2021

Zitierform

Tags