Results 71 to 80 of about 80,002 (216)

What Do Large Language Models Know About Materials?

Advanced Engineering Materials, EarlyView.
If large language models (LLMs) are to be used inside the material discovery and engineering process, they must be benchmarked for the accurateness of intrinsic material knowledge. The current work introduces 1) a reasoning process through the processing–structure–property–performance chain and 2) a tool for benchmarking knowledge of LLMs concerning ...
Adrian Ehrenhofer, Thomas Wallmersperger, Gianaurelio Cuniberti   +2 more
wiley   +1 more source

Query Rewriting Using Monolingual Statistical Machine Translation

Computational Linguistics, 2021
Stefan Riezler, Yi Liu
doaj   +1 more source

Using artificial intelligence tools for translating computer terminology

Acta Academiae Beregsasiensis, Philologica
The emergence of artificial intelligence (AI) technologies has significantly transformed the field of translation, streamlining processes through automation and enhancing both efficiency and accuracy.
Maryna Tymchyk, Natalia Drabov
doaj   +1 more source

Is an Apple an Orange? A Large Language Model Benchmark for Candidate Term Extraction and Subclass Decisions Against Upper Ontologies in Engineering and Materials Science

Advanced Engineering Materials, EarlyView.
Building machine‐readable vocabularies for materials science is slow, expert‐driven work. This study benchmarks 13 large language models on two of its first steps: finding candidate terms in engineering articles and deciding where they belong in a class hierarchy.
Thomas Bjarsch, Maximilian Holland, Klaus Drechsler, Johannes Schilp   +3 more
wiley   +1 more source

Optimizing Statistical Machine Translation for Text Simplification

Transactions of the Association for Computational Linguistics, 2021
Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen, Chris Callison-Burch   +4 more
doaj   +1 more source

The PRIMA Thesaurus for Materials Science and Engineering

Advanced Engineering Materials, EarlyView.
The PRIMA Thesaurus is a structured vocabulary designed to improve how materials science data is described and shared. Developed with input from multiple experts, it enables clear documentation of research workflows, data exchange, and reuse across platforms.
Rossella Aversa, Alexey Boubnov, Dario De Angelis, Catriona Eschke, Maximilian Kabbe, Felix Kraus, Mirco Panighel, Richard Thelen, Davide Valentinis   +8 more
wiley   +1 more source

Optimization for Statistical Machine Translation: A Survey

Computational Linguistics, 2023
Graham Neubig, Taro Watanabe
doaj   +1 more source

A Lightweight Procedural Layer for Hybrid Experimental–Computational Workflows in Materials Science

Advanced Engineering Materials, EarlyView.
We unveil a prototype hybrid‐workflow framework that fuses automatedcomputation with hands‐on experiments. Built atop pyiron, a lightweight, parameterized layer translates procedure descriptions into executable manual steps, syncing instrument settings, human interventions, and data capture in real‐time today.
Steffen Brinckmann, Sarath Menon, Raphael Röske, Johannes Steinhülb, Michael Selzer, Jan Janssen, Tilmann Hickel, Ruth Schwaiger, Jörg Neugebauer   +8 more
wiley   +1 more source

Modular Critical Element Recycling Platform Using a Nanoporous Additively Manufactured Gyroid

Advanced Engineering Materials, EarlyView.
A modular recycling platform integrates 3D‐printed nanoporous gyroid structures to enable efficient critical element recovery. This system utilizes a hierarchical architecture, combining macroscopic channels with polymerization‐induced nanoscale porosity. By systematically tuning structural wall thickness and resin formulation, the platform achieves an
Xiangyu Gao, Keldy Mason, Mert Gülçür, Rachel Paddock‐Lamb, Prince Alvin Fofanah, Zachariah A. Page, Michael Cullinan   +6 more
wiley   +1 more source