FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385984648> ?p ?o ?g. }

• W4385984648 endingPage "e1511" @default.
• W4385984648 startingPage "e1511" @default.
• W4385984648 abstract "This article proposes a methodology that uses machine learning algorithms to extract actions from structured chemical synthesis procedures, thereby bridging the gap between chemistry and natural language processing. The proposed pipeline combines ML algorithms and scripts to extract relevant data from USPTO and EPO patents, which helps transform experimental procedures into structured actions. This pipeline includes two primary tasks: classifying patent paragraphs to select chemical procedures and converting chemical procedure sentences into a structured, simplified format. We employ artificial neural networks such as long short-term memory, bidirectional LSTMs, transformers, and fine-tuned T5. Our results show that the bidirectional LSTM classifier achieved the highest accuracy of 0.939 in the first task, while the Transformer model attained the highest BLEU score of 0.951 in the second task. The developed pipeline enables the creation of a dataset of chemical reactions and their procedures in a structured format, facilitating the application of AI-based approaches to streamline synthetic pathways, predict reaction outcomes, and optimize experimental conditions. Furthermore, the developed pipeline allows for creating a structured dataset of chemical reactions and procedures, making it easier for researchers to access and utilize the valuable information in synthesis procedures." @default.
• W4385984648 created "2023-08-19" @default.
• W4385984648 creator A5038039797 @default.
• W4385984648 creator A5043042273 @default.
• W4385984648 creator A5054995973 @default.
• W4385984648 creator A5092662387 @default.
• W4385984648 date "2023-08-18" @default.
• W4385984648 modified "2023-10-16" @default.
• W4385984648 title "Deep learning-based automatic action extraction from structured chemical synthesis procedures" @default.
• W4385984648 cites W1976892175 @default.
• W4385984648 cites W2034354062 @default.
• W4385984648 cites W2072550304 @default.
• W4385984648 cites W2091753323 @default.
• W4385984648 cites W2101105183 @default.
• W4385984648 cites W2104489082 @default.
• W4385984648 cites W2250539671 @default.
• W4385984648 cites W2324964582 @default.
• W4385984648 cites W2493916176 @default.
• W4385984648 cites W2606363443 @default.
• W4385984648 cites W2747592475 @default.
• W4385984648 cites W2769423117 @default.
• W4385984648 cites W2785942661 @default.
• W4385984648 cites W2899663614 @default.
• W4385984648 cites W2911361106 @default.
• W4385984648 cites W2917049430 @default.
• W4385984648 cites W2950635152 @default.
• W4385984648 cites W2965373594 @default.
• W4385984648 cites W2984811147 @default.
• W4385984648 cites W2986729576 @default.
• W4385984648 cites W3000274722 @default.
• W4385984648 cites W3034021666 @default.
• W4385984648 cites W3038024393 @default.
• W4385984648 cites W3043647281 @default.
• W4385984648 cites W3044968736 @default.
• W4385984648 cites W3047170760 @default.
• W4385984648 cites W3082330004 @default.
• W4385984648 cites W3097717858 @default.
• W4385984648 cites W3098269892 @default.
• W4385984648 cites W3103092523 @default.
• W4385984648 cites W3118349318 @default.
• W4385984648 cites W3128902667 @default.
• W4385984648 cites W3132956480 @default.
• W4385984648 cites W3146601652 @default.
• W4385984648 cites W3153977456 @default.
• W4385984648 cites W3158607076 @default.
• W4385984648 cites W3161494759 @default.
• W4385984648 cites W3179950556 @default.
• W4385984648 cites W3194005300 @default.
• W4385984648 cites W3198229735 @default.
• W4385984648 cites W3200122731 @default.
• W4385984648 cites W3202156390 @default.
• W4385984648 cites W3206841862 @default.
• W4385984648 cites W3209951148 @default.
• W4385984648 cites W4220670676 @default.
• W4385984648 cites W4221166186 @default.
• W4385984648 cites W4224943830 @default.
• W4385984648 cites W4226189107 @default.
• W4385984648 cites W4284672872 @default.
• W4385984648 cites W4287180316 @default.
• W4385984648 cites W4287887197 @default.
• W4385984648 cites W4288089799 @default.
• W4385984648 cites W4288108708 @default.
• W4385984648 cites W4289677850 @default.
• W4385984648 cites W4294133266 @default.
• W4385984648 cites W4301372551 @default.
• W4385984648 cites W4307468223 @default.
• W4385984648 cites W4310884106 @default.
• W4385984648 cites W4313483387 @default.
• W4385984648 cites W4313525671 @default.
• W4385984648 cites W4385245566 @default.
• W4385984648 doi "https://doi.org/10.7717/peerj-cs.1511" @default.
• W4385984648 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37705639" @default.
• W4385984648 hasPublicationYear "2023" @default.
• W4385984648 type Work @default.
• W4385984648 citedByCount "0" @default.
• W4385984648 crossrefType "journal-article" @default.
• W4385984648 hasAuthorship W4385984648A5038039797 @default.
• W4385984648 hasAuthorship W4385984648A5043042273 @default.
• W4385984648 hasAuthorship W4385984648A5054995973 @default.
• W4385984648 hasAuthorship W4385984648A5092662387 @default.
• W4385984648 hasBestOaLocation W43859846481 @default.
• W4385984648 hasConcept C119857082 @default.
• W4385984648 hasConcept C121332964 @default.
• W4385984648 hasConcept C154945302 @default.
• W4385984648 hasConcept C165801399 @default.
• W4385984648 hasConcept C174348530 @default.
• W4385984648 hasConcept C199360897 @default.
• W4385984648 hasConcept C204321447 @default.
• W4385984648 hasConcept C31258907 @default.
• W4385984648 hasConcept C41008148 @default.
• W4385984648 hasConcept C43521106 @default.
• W4385984648 hasConcept C61423126 @default.
• W4385984648 hasConcept C62520636 @default.
• W4385984648 hasConcept C66322947 @default.
• W4385984648 hasConcept C95623464 @default.
• W4385984648 hasConceptScore W4385984648C119857082 @default.
• W4385984648 hasConceptScore W4385984648C121332964 @default.
• W4385984648 hasConceptScore W4385984648C154945302 @default.

• next