ProgramMaster Logo
Conference Tools for 2023 TMS Annual Meeting & Exhibition
Register as a New User
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Abstract
Meeting 2023 TMS Annual Meeting & Exhibition
Symposium Hume-Rothery Symposium on First-Principles Materials Design
Presentation Title Advances in Natural Language Processing for Building Datasets in Materials
Author(s) Elsa Olivetti
On-Site Speaker (Planned) Elsa Olivetti
Abstract Scope The heuristic nature of materials synthesis limits researchers' ability to extend materials genome initiative-type approaches to methods to make novel materials or extend existing materials to new, controlled morphologies and microstructures. A number of recent informatics-based approaches have shown that machine learning models can learn synthesis conditions given sufficient data. Machine readable databases of inorganic material fabrication and processing are still limited since the underlying information is present only in unstructured databases such as archives of published scientific literature. Recent work has shown how natural language processing can be used to extract synthesis specific information from texts. The techniques used for these extractions include sequence to sequence tagging algorithms employing recurrent neural networks, large language models, and language dependency parsing using linguistic grammar trees. This presentation will reflect on use of the latest methods in transformer based neural network architecture to extract information from the scientific literature.
Proceedings Inclusion? Planned:
Keywords Machine Learning,


Advances in Natural Language Processing for Building Datasets in Materials
Available methods for predicting materials synthesizability using computational and machine learning approaches
Computational Design of Multicomponent Nanoparticle Morphologies
Computational Discovery of Materials with Fast Oxygen Kinetics
Computational materials design and discovery for next-generation solid-state batteries
Computational tools for the generation of high-dimensional phase diagrams
Design of Novel Electrode and Solid Electrolyte Materials Guided by Crystal Structure Characterization and Understanding
Disorder and degradation in rock-salt-type lithium-ion battery cathodes
Double Descent, Linear Regression, and Fundamental Questions in Alloy Model Building
Dynamic stability design of materials for solid-state batteries
Establishing links between synthesis, defect landscape, and ion conduction in halide-type solid electrolytes
First principle design of high entropy materials for energy storage and conversion
From atom to system - how to build better batteries
Holistic Integration of Experimental and Computational Data and Simple Empirical Models for Diffusion Coefficients of Metallic Solid Solutions
Learning Rules for High-Throughput Screening of Materials Properties and Functions
Linking phenomenological theories of materials to electronic structure
Machine Learning Assisted Materials Generation
Machine Learning for Simulating Complex Energy Materials with Non-Crystalline Structures - A graph deep learning database of materials properties
Microstructure modeling with machine learning
Millisecond-ion Transport in Mixed Polyanion in Energy Materials
New battery chemistry from conventional layered cathode materials for advanced lithium-ion batteries
Origin of the Invar effect
Plasmonic high-entropy carbides
Predicting synthesis and synthesizability beyond the DFT convex hull
Probing Local Structures, Electronic Structures and Defects in Battery Materials by Combining NMR and DFT Calculations
Structure determination – from materials design to characterization
The Stewardship of a Materials Genome
Understanding Complex Materials and Interfaces through Molecular Dynamics Simulations
Understanding key properties of disordered rock-salt Li-ion cathode materials based on ab initio calculations and experiments
William Hume-Rothery Award Lecture: Ab initio Thermodynamics and Kinetics from Alloys to Complex Oxides

Questions about ProgramMaster? Contact