Logo des Repositoriums
 

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

Kurzanzeige
dc.contributor.authorWeigelt, Sebastian
dc.contributor.authorSteurer, Vanessa
dc.contributor.authorHey, Tobias
dc.contributor.authorTichy, Walter
dc.contributor.editorKoziolek, Anne
dc.contributor.editorSchaefer, Ina
dc.contributor.editorSeidl, Christoph
dc.date.accessioned2020-12-17T11:58:04Z
dc.date.available2020-12-17T11:58:04Z
dc.date.issued2021
dc.description.abstractWith 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.en
dc.identifier.doi10.18420/SE2021_46
dc.identifier.isbn978-3-88579-704-3
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/34543
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofSoftware Engineering 2021
dc.relation.ispartofseriesecture Notes in Informatics (LNI) - Proceedings, Volume P-310
dc.subjectProgramming in Natural Language
dc.subjectEnd-User Programming
dc.subjectDeep Learning
dc.subjectAI
dc.subjectNLP
dc.titleProgramming in Natural Language with fuSE: Synthesizing Methods from Spoken Utterances Using Deep Natural Language Understandingen
dc.typeText/ConferencePaper
gi.citation.endPage118
gi.citation.publisherPlaceBonn
gi.citation.startPage117
gi.conference.date22.-26. Februar 2021
gi.conference.locationBraunschweig/Virtuell

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
B1-45.pdf
Größe:
132.28 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P310 - Software Engineering 2021