Enriching Artificial Intelligence Explanations with Knowledge Fragments

Future Internet

Elena Trajkova¹  Dunja Mladenić²  Inna Novalija²  Klemen Kenda³  Jože Rožanec³  Patrik Zajec³  Blaž Fortuna⁴ 

[1] Faculty of Electrical Engineering, University of Ljubljana, Tržaška c. 25, 1000 Ljubljana, Slovenia;Jožef Stefan Institute, Jamova 39, 1000 Ljubljana, Slovenia;Jožef Stefan International Postgraduate School, Jamova 39, 1000 Ljubljana, Slovenia;Qlector d.o.o., Rovšnikova 7, 1000 Ljubljana, Slovenia;

关键词: explainable artificial intelligence;    human-centric artificial intelligence;    smart manufacturing;    demand forecasting;    Industry 4.0;    Industry 5.0;   

DOI  :  10.3390/fi14050134

来源: DOAJ

【 摘 要 】

Artificial intelligence models are increasingly used in manufacturing to inform decision making. Responsible decision making requires accurate forecasts and an understanding of the models’ behavior. Furthermore, the insights into the models’ rationale can be enriched with domain knowledge. This research builds explanations considering feature rankings for a particular forecast, enriching them with media news entries, datasets’ metadata, and entries from the Google knowledge graph. We compare two approaches (embeddings-based and semantic-based) on a real-world use case regarding demand forecasting. The embeddings-based approach measures the similarity between relevant concepts and retrieved media news entries and datasets’ metadata based on the word movers’ distance between embeddings. The semantic-based approach recourses to wikification and measures the Jaccard distance instead. The semantic-based approach leads to more diverse entries when displaying media events and more precise and diverse results regarding recommended datasets. We conclude that the explanations provided can be further improved with information regarding the purpose of potential actions that can be taken to influence demand and to provide “what-if” analysis capabilities.

【 授权许可】

Unknown