Text mining facilitates materials discovery

(DOE/Lawrence Berkeley National Laboratory) Researchers at Lawrence Berkeley National Laboratory have shown that an algorithm with no training in materials science can scan the text of millions of papers and uncover new scientific knowledge. They collected 3.3 million abstracts of published materials science papers and fed them into an algorithm called Word2vec. By analyzing relationships between words the algorithm was able to predict discoveries of new thermoelectric materials years in advance and suggest as-yet unknown materials as candidates for thermoelectric materials.

Text mining facilitates materials discovery

Nature, Published online: 03 July 2019; doi:10.1038/d41586-019-01978-xComputer algorithms can be used to analyse text to find semantic relationships between words without human ...

Wed 3 Jul 19 from Nature News

Unsupervised word embeddings capture latent knowledge from materials science literature

Nature, Published online: 03 July 2019; doi:10.1038/s41586-019-1335-8Natural language processing algorithms applied to three million materials science abstracts uncover relationships ...

Wed 3 Jul 19 from Nature News

Machine-learning algorithms can discover new things

Research shows they could even help us cut through the paperwork. Nick Carne reports.

Wed 3 Jul 19 from Cosmos Magazine

With little training, machine-learning algorithms can uncover hidden scientific knowledge

Sure, computers can be used to play grandmaster-level chess (chess_computer), but can they make scientific discoveries? Researchers at the U.S. Department of Energy's Lawrence Berkeley National ...

Wed 3 Jul 19 from TechXplore

With Little Training, Machine-Learning Algorithms Can Uncover Hidden Scientific Knowledge, Thu 4 Jul 19 from Science Blog

With little training, machine-learning algorithms can uncover hidden scientific knowledge, Wed 3 Jul 19 from ScienceDaily

With Little Training, Machine-Learning Algorithms Can Uncover Hidden Scientific Knowledge, Wed 3 Jul 19 from Newswise

With little training, machine-learning algorithms can uncover hidden scientific knowledge, Wed 3 Jul 19 from Eurekalert

Text mining could help in the rational design of new materials

A machine-learning algorithm with no training in materials science can unearth hidden knowledge in scientific publications by analysing the semantic relationships between words The post Text ...

Thu 4 Jul 19 from Physicsworld Blog

  • Pages: 1

Total number of sources: 9

Bookmark

Bookmark and Share