{"@type": "dcat:Dataset", "accessLevel": "public", "accrualPeriodicity": "irregular", "bureauCode": ["006:55"], "contactPoint": {"fn": "June W. Lau", "hasEmail": "mailto:june.lau@nist.gov"}, "description": "This is a collection of code written by Maurice Curran that was used to process the Microscopy and Microanalysis conference proceeding corpus into word products described in the publication \"NLP-Driven Electron Microscopy Ontology Development\". The scripts are written in Python, to  be used in the following order:1. SettingUpTextFiles.py and CopyingText.py to get the raw text files; 2. SentenceConversion.py; 3. reference_remover.py; 4. testing.py and testingavg.py; 5. SentenceCreator.py; 6. matscholar_model.py to get matscholar tags; 7. training_model_gensim.py to get gensim model;8. word2vecscript.py and gensim_visual.py;", "distribution": [{"description": "This zip file contains a set of scripts that extracts frequently occurring words from the conference proceedings of Microscopy & Microanalysis between the years of 2002 and 2019.", "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-3198/PythonFiles_Maurice_clean.zip", "mediaType": "application/zip", "title": "NLP code to produce words about electron microscopy"}], "identifier": "ark:/88434/mds2-3198", "issued": "2024-09-05", "keyword": ["NLP", "Natural language processing", "controlled vocabulary", "electron microscopy", "ontology"], "landingPage": "https://data.nist.gov/od/id/mds2-3198", "language": ["en"], "license": "https://www.nist.gov/open/license", "modified": "2021-12-31 00:00:00", "programCode": ["006:045"], "publisher": {"@type": "org:Organization", "name": "National Institute of Standards and Technology"}, "references": ["https://doi.org/10.1007/s40192-024-00378-y"], "theme": ["Information Technology:Data and informatics", "Materials:Materials characterization", "Materials:Modeling and computational material science"], "title": "Code used to produce terms list in the work \"NLP-Driven Electron Microscopy Ontology Development\""}