Human-understandable and machine-processable explanations for sub-symbolic predictions

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

56 Downloads (Pure)

Abstract

HESIP is a hybrid machine learning system in which a sub-symbolic machine learning component makes a prediction for an image classification and afterwards a symbolic machine learning component learns probabilistic rules that are used to explain that prediction. In this paper, we present an extension to HESIP that generates human-understandable and machine-processable explanations in a controlled natural language for the learned probabilistic rules. In order to achieve this, the literals of the probabilistic rules are first reordered, and then aggregated and disambiguated according to linguistic principles so that the rules can be verbalised with a bi-directional grammar. A human-in-the-loop can modify incorrect explanations and the same bi-directional grammar can be used to process these explanations to improve the decision process of the machine.
Original languageEnglish
Title of host publicationSeventh International Workshop on Controlled Natural Language, CNL 2020/21
Subtitle of host publicationWorkshop Proceedings
EditorsTobias Kuhn, Silvie Spreeuwenberg, Stijn Hoppenbrouwers, Norbert E. Fuchs
Place of PublicationStroudsburg, PA
PublisherAssociation for Computational Linguistics (ACL)
Number of pages5
Publication statusPublished - 2021
Event7th International Workshop on Controlled Natural Language, CNL 2020/21 - Amsterdam, Netherlands
Duration: 8 Sept 20219 Sept 2021

Conference

Conference7th International Workshop on Controlled Natural Language, CNL 2020/21
Country/TerritoryNetherlands
CityAmsterdam
Period8/09/219/09/21

Bibliographical note

Copyright the Publisher 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Fingerprint

Dive into the research topics of 'Human-understandable and machine-processable explanations for sub-symbolic predictions'. Together they form a unique fingerprint.

Cite this