Automated pipeline for superalloy data by text mining

Wang, Weiren; Jiang, Xue; Tian, Shaohan; Liu, Pei; Dang, Depeng; Su, Yanjing; Lookman, Turab; Xie, Jun

doi:10.1038/s41524-021-00687-2

Cited by 49 publications

(37 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The initial corpus we use is to use the NER method to mark the superalloy name and property value in a sentence. The specific method of NER is detailed in our previous article 11 . However, the initial corpus marks all the superalloy names and property values in a sentence, depending on NER can not accurately find the matching mode of superalloy names and property values if there are multiple superalloy names and property values in a sentence.…”

Section: Resultsmentioning

confidence: 99%

“…For superalloys in materials, we use rule-based methods to classify sentences containing the name of the superalloys and corresponding property values from more than 14,425 full texts of scientific journal articles related to material. Similar to our previous work 11 , these articles are accessed through Elsevier Research Products APIs allowing anyone that can obtain an API Key and use the APIs for non-commercial purposes free of charge. The detailed information about Elsevier Research Products APIs can refer https://dev.elsevier.com .…”

Section: Resultsmentioning

confidence: 99%

“…It is time-consuming to rely solely on human manual extraction 6 . So, automatic data extraction of organic and inorganic chemical substances from articles in the fields of chemistry and materials science have made their sense using NLP techniques 7 – 11 .…”

Section: Introductionmentioning

confidence: 99%

“…Unfortunately, there are relatively few papers on many materials subjects, such as superalloys, extracting the required information from the paper becomes a tricky job. In our previous work 11 , we developed an NLP pipeline to capture both chemical composition and property data from superalloys scientific literature. A rule-based Named Entity Recognition (NER) method and a distance-based heuristic multiple-relation extraction algorithm for the pipeline were proposed to overcome the drawback of limited training corpus labels, and achieve high precision and recall simultaneously.…”

Section: Introductionmentioning

confidence: 99%

“…Our contributions are summarized as follows: New IE framework is proposed for materials using the semi-supervised method in machine learning to automatically generate corpus. These works are completed based on the previous work 11 , and further extract the information in the material field. ON-LSTM is used to complete the task of IE.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Materials information extraction via automatically generated corpus

et al. 2022

Self Cite

View full text Add to dashboard Cite

Information Extraction (IE) in Natural Language Processing (NLP) aims to extract structured information from unstructured text to assist a computer in understanding natural language. Machine learning-based IE methods bring more intelligence and possibilities but require an extensive and accurate labeled corpus. In the materials science domain, giving reliable labels is a laborious task that requires the efforts of many professionals. To reduce manual intervention and automatically generate materials corpus during IE, in this work, we propose a semi-supervised IE framework for materials via automatically generated corpus. Taking the superalloy data extraction in our previous work as an example, the proposed framework using Snorkel automatically labels the corpus containing property values. Then Ordered Neurons-Long Short-Term Memory (ON-LSTM) network is adopted to train an information extraction model on the generated corpus. The experimental results show that the F1-score of γ’ solvus temperature, density and solidus temperature of superalloys are 83.90%, 94.02%, 89.27%, respectively. Furthermore, we conduct similar experiments on other materials, the experimental results show that the proposed framework is universal in the field of materials.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Materials information extraction via automatically generated corpus

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

Methods, progresses, and opportunities of materials informatics

Li,

Zheng

2023

InfoMat

View full text Add to dashboard Cite

As an implementation tool of data intensive scientific research methods, machine learning (ML) can effectively shorten the research and development (R&D) cycle of new materials by half or even more. ML shows great potential in the combination with other scientific research technologies, especially in the processing and classification of large amounts of material data from theoretical calculation and experimental characterization. It is very important to systematically understand the research ideas of material informatics to accelerate the exploration of new materials. Here, we provide a comprehensive introduction to the most commonly used ML modeling methods in material informatics with classic cases. Then, we review the latest progresses of prediction models, which focus on new processing–structure–properties–performance (PSPP) relationships in some popular material systems, such as perovskites, catalysts, alloys, two‐dimensional materials, and polymers. In addition, we summarize the recent pioneering researches in innovation of material research technology, such as inverse design, ML interatomic potentials, and microtopography characterization assistance, as new research directions of material informatics. Finally, we comprehensively provide the most significant challenges and outlooks related to the future innovation and development in the field of material informatics. This review provides a critical and concise appraisal for the applications of material informatics, and a systematic and coherent guidance for material scientists to choose modeling methods based on required materials and technologies.

show abstract

Ordering phenomena in ternary transition‐metal dichalcogenides: Critical role of lattice symmetry and vdW interaction

Zhang,

Zhu,

Liu

et al. 2023

Materials Genome Engineering Advances

View full text Add to dashboard Cite

Concentrated solid solution materials with huge compositional design space and normally unexpected property attract extensive interests of researchers. In these emerging materials, local composition fluctuation such as short‐range order (SRO), has been observed and found to have nontrivial effects on material properties, and thus can be utilized as an additional degree of freedom for material optimization. To exploit SRO, its interplay with factors beyond element‐level property, including lattice symmetry and bonding environment, should be clarified. In this work by using layered transition‐metal dichalcogenide Mo(X0.5X′0.5)2 (X/X′ = O, S, Se, or Te) with mixed element in the non‐metal sublattice as the platform, the ordering phenomena are systematically studied using multiscale simulations. As expected, electronegativity difference between X and X′ strongly regulates SRO. Additionally, SRO and long‐range order (LRO) are observed in the 2H and T/T′ phase of MoXX′, respectively, indicating a strong influence of lattice symmetry on SRO. More importantly, as vdW interaction is introduced, the SRO structure in 2H‐MoXX′ bilayer can be re‐configured, while the LRO in T/T′‐MoXX′ remains unchanged. Electronic insights for SRO and the resultant property variation are obtained. This work presents a thorough understanding of SRO in bonding complex systems, benefiting the SRO‐guided material designs.

show abstract

Automated pipeline for superalloy data by text mining

Cited by 49 publications

References 45 publications

Materials information extraction via automatically generated corpus

Materials information extraction via automatically generated corpus

Methods, progresses, and opportunities of materials informatics

Ordering phenomena in ternary transition‐metal dichalcogenides: Critical role of lattice symmetry and vdW interaction

Contact Info

Product

Resources

About