DE eng

Search in the Catalogues and Directories

Hits 1 – 9 of 9

1
Eine agentenbasierte Architektur für Programmierung mit gesprochener Sprache ...
Weigelt, Sebastian. - : KIT Scientific Publishing, 2022
BASE
Show details
2
Eine agentenbasierte Architektur für Programmierung mit gesprochener Sprache
Weigelt, Sebastian. - : KIT Scientific Publishing, Karlsruhe, 2022
BASE
Show details
3
Eine agentenbasierte Architektur für Programmierung mit gesprochener Sprache ...
Weigelt, Sebastian. - : Karlsruher Institut für Technologie (KIT), 2021
BASE
Show details
4
Eine agentenbasierte Architektur für Programmierung mit gesprochener Sprache
Weigelt, Sebastian. - : KIT-Bibliothek, Karlsruhe, 2021
BASE
Show details
5
Programming in Natural Language with fuSE : Synthesizing Methods from Spoken Utterances Using Deep Natural Language Understanding ...
BASE
Show details
6
Towards Programming in Natural Language: Learning New Functions from Spoken Utterances ...
Weigelt, Sebastian; Steurer, Vanessa; Hey, Tobias. - : World Scientific Publishing, 2020
BASE
Show details
7
Towards Programming in Natural Language: Learning New Functions from Spoken Utterances
In: International journal of semantic computing, 14 (2), 249–272 ; ISSN: 1793-351X, 1793-7108 (2020)
BASE
Show details
8
Programming in Natural Language with fuSE : Synthesizing Methods from Spoken Utterances Using Deep Natural Language Understanding
Weigelt, Sebastian; Hey, Tobias; Tichy, Walter F.; Steurer, Vanessa. - : Association for Computational Linguistics, 2020
Abstract: The key to effortless end-user programming is natural language. We examine how to teach intelligent systems new functions, expressed in natural language. As a first step, we collected 3168 samples of teaching efforts in plain English. Then we built fuSE, a novel system that translates English function descriptions into code. Our approach is three-tiered and each task is evaluated separately. We first classify whether an intent to teach new functionality is present in the utterance (accuracy: 97.7% using BERT). Then we analyze the linguistic structure and construct a semantic model (accuracy: 97.6% using a BiLSTM). Finally, we synthesize the signature of the method, map the intermediate steps (instructions in the method body) to API calls and inject control structures (F1: 67.0% with information retrieval and knowledge-based methods). In an end-to-end evaluation on an unseen dataset fuSE synthesized 84.6% of the method signatures and 79.2% of the API calls correctly.
Keyword: DATA processing & computer science; ddc:004; info:eu-repo/classification/ddc/004
URL: https://publikationen.bibliothek.kit.edu/1000124407
https://publikationen.bibliothek.kit.edu/1000124407/89592930
https://doi.org/10.5445/IR/1000124407
BASE
Hide details
9
Zielsystemunabhängige Quelltextsynthese aus natürlicher Sprache
Kiesel, Viktor. - : Karlsruher Institut für Technologie, 2019
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
9
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern