Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225647568> ?p ?o ?g. }
- W4225647568 endingPage "134" @default.
- W4225647568 startingPage "134" @default.
- W4225647568 abstract "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." @default.
- W4225647568 created "2022-05-05" @default.
- W4225647568 creator A5007088891 @default.
- W4225647568 creator A5009957515 @default.
- W4225647568 creator A5017413169 @default.
- W4225647568 creator A5019788602 @default.
- W4225647568 creator A5054995729 @default.
- W4225647568 creator A5063095022 @default.
- W4225647568 creator A5067396725 @default.
- W4225647568 date "2022-04-29" @default.
- W4225647568 modified "2023-10-11" @default.
- W4225647568 title "Enriching Artificial Intelligence Explanations with Knowledge Fragments" @default.
- W4225647568 cites W1972835575 @default.
- W4225647568 cites W1988917059 @default.
- W4225647568 cites W2038849095 @default.
- W4225647568 cites W2051361041 @default.
- W4225647568 cites W2054940711 @default.
- W4225647568 cites W2070665593 @default.
- W4225647568 cites W2096908543 @default.
- W4225647568 cites W2147619096 @default.
- W4225647568 cites W2150181698 @default.
- W4225647568 cites W2166558062 @default.
- W4225647568 cites W2170125973 @default.
- W4225647568 cites W2346007556 @default.
- W4225647568 cites W2493343568 @default.
- W4225647568 cites W2559490222 @default.
- W4225647568 cites W2767828640 @default.
- W4225647568 cites W2805720864 @default.
- W4225647568 cites W2809752678 @default.
- W4225647568 cites W2811256013 @default.
- W4225647568 cites W2891503716 @default.
- W4225647568 cites W2908815325 @default.
- W4225647568 cites W2953884995 @default.
- W4225647568 cites W2968770299 @default.
- W4225647568 cites W2981697369 @default.
- W4225647568 cites W2981731882 @default.
- W4225647568 cites W2982925393 @default.
- W4225647568 cites W2986257753 @default.
- W4225647568 cites W2997638503 @default.
- W4225647568 cites W3014346580 @default.
- W4225647568 cites W3036068473 @default.
- W4225647568 cites W3043941844 @default.
- W4225647568 cites W3093718041 @default.
- W4225647568 cites W3094127673 @default.
- W4225647568 cites W3124009622 @default.
- W4225647568 cites W3131175048 @default.
- W4225647568 cites W3136296618 @default.
- W4225647568 cites W3154992862 @default.
- W4225647568 cites W3159651487 @default.
- W4225647568 cites W3159906225 @default.
- W4225647568 cites W3185348919 @default.
- W4225647568 cites W3194459689 @default.
- W4225647568 cites W3197347140 @default.
- W4225647568 cites W3205172848 @default.
- W4225647568 cites W3207487028 @default.
- W4225647568 cites W3212279072 @default.
- W4225647568 cites W3214886350 @default.
- W4225647568 cites W4243342770 @default.
- W4225647568 cites W4250135710 @default.
- W4225647568 doi "https://doi.org/10.3390/fi14050134" @default.
- W4225647568 hasPublicationYear "2022" @default.
- W4225647568 type Work @default.
- W4225647568 citedByCount "4" @default.
- W4225647568 countsByYear W42256475682022 @default.
- W4225647568 countsByYear W42256475682023 @default.
- W4225647568 crossrefType "journal-article" @default.
- W4225647568 hasAuthorship W4225647568A5007088891 @default.
- W4225647568 hasAuthorship W4225647568A5009957515 @default.
- W4225647568 hasAuthorship W4225647568A5017413169 @default.
- W4225647568 hasAuthorship W4225647568A5019788602 @default.
- W4225647568 hasAuthorship W4225647568A5054995729 @default.
- W4225647568 hasAuthorship W4225647568A5063095022 @default.
- W4225647568 hasAuthorship W4225647568A5067396725 @default.
- W4225647568 hasBestOaLocation W42256475681 @default.
- W4225647568 hasConcept C103278499 @default.
- W4225647568 hasConcept C115961682 @default.
- W4225647568 hasConcept C119857082 @default.
- W4225647568 hasConcept C130318100 @default.
- W4225647568 hasConcept C134306372 @default.
- W4225647568 hasConcept C136764020 @default.
- W4225647568 hasConcept C154945302 @default.
- W4225647568 hasConcept C203519979 @default.
- W4225647568 hasConcept C207685749 @default.
- W4225647568 hasConcept C23123220 @default.
- W4225647568 hasConcept C2522767166 @default.
- W4225647568 hasConcept C2987255567 @default.
- W4225647568 hasConcept C33923547 @default.
- W4225647568 hasConcept C36503486 @default.
- W4225647568 hasConcept C41008148 @default.
- W4225647568 hasConcept C73555534 @default.
- W4225647568 hasConcept C93518851 @default.
- W4225647568 hasConceptScore W4225647568C103278499 @default.
- W4225647568 hasConceptScore W4225647568C115961682 @default.
- W4225647568 hasConceptScore W4225647568C119857082 @default.
- W4225647568 hasConceptScore W4225647568C130318100 @default.
- W4225647568 hasConceptScore W4225647568C134306372 @default.
- W4225647568 hasConceptScore W4225647568C136764020 @default.
- W4225647568 hasConceptScore W4225647568C154945302 @default.