English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Although gold nanorods have been the subject of much research, the pathwaysfor controlling their shape and thereby their optical properties remain largelyheuristically understood. Although it is apparent that the simultaneouspresence of and interaction between various reagents during synthesis controlthese properties, computational and experimental approaches for exploring thesynthesis space can be either intractable or too time-consuming in practice.This motivates an alternative approach leveraging the wealth of synthesisinformation already embedded in the body of scientific literature by developingtools to extract relevant structured data in an automated, high-throughputmanner. To that end, we present an approach using the powerful GPT-3 languagemodel to extract structured multi-step seed-mediated growth procedures andoutcomes for gold nanorods from unstructured scientific text. GPT-3 promptcompletions are fine-tuned to predict synthesis templates in the form of JSONdocuments from unstructured text input with an overall accuracy of $86\%$. Theperformance is notable, considering the model is performing simultaneous entityrecognition and relation extraction. We present a dataset of 11,644 entitiesextracted from 1,137 papers, resulting in 268 papers with at least one completeseed-mediated gold nanorod growth procedure and outcome for a total of 332complete procedures.

Extracting Structured Seed-Mediated Gold Nanorod Growth Procedures from Literature with GPT-3