KIT | KIT-Bibliothek | Impressum | Datenschutz

Roger that! Learning How Laypersons Teach New Functions to Intelligent Systems

Weigelt, Sebastian; Steurer, Vanessa; Hey, Tobias; Tichy, Walter F.

Abstract (englisch):
Intelligent systems are rather smart today but still limited to built-in functionality. To break through this barrier, future systems must allow users to easily adapt the system by themselves. For humans the most natural way to communicate is talking. But what if users want to extend the systems’ functionality with nothing but natural language? Then intelligent systems must understand how laypersons teach new skills. To grasp the semantics of such teaching sequences, we have defined a hierarchical classification task. On the first level, we consider the existence of a teaching intent in an utterance; on the second, we classify the distinct semantic parts of teaching sequences: declaration of a new function, specification of intermediate steps, and superfluous information. We evaluate twelve machine learning techniques with multiple configurations tailored to this task ranging from classical approaches such as naı̈ve-bayes to modern techniques such as bidirectional LSTMs and task-oriented adaptations. On the first level convolutional neural networks achieve the best accuracy (96.6%). For the second task, bidirectional LSTMs are the most accurate (98.8%). ... mehr

Open Access Logo


Preprint §
DOI: 10.5445/IR/1000117897
Veröffentlicht am 26.03.2020
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Programmstrukturen und Datenorganisation (IPD)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2020
Sprache Englisch
Identifikator ISBN: 978-1-72816-332-1
KITopen-ID: 1000117897
Erschienen in Proceedings of the 2020 IEEE 14th International Conference on Semantic Computing (ICSC)
Veranstaltung 14th IEEE International Conference on Semantic Computing (ICSC 2020), San Diego, CA, USA, 03.02.2020 – 05.02.2020
Verlag IEEE, Piscataway (NJ)
Seiten 93–100
Vorab online veröffentlicht am 12.03.2020
Schlagwörter Machine Learning, Programming in Natural Language, Natural Language Understanding, Natural Language Processing, Neural Networks, Artificial Neural Networks, Recurrent Neural Networks, Convolutional Neural Networks, Intelligent System, End User Programming, Artificial Intelligence
Nachgewiesen in Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page