Abstract：Maximizing Equitable Reach and Accessibility of ETDs This poster addresses accessibility issues of electronic theses and dissertationsETDsin digital librariesDLsETDs are available primarily as PDF fileswhich present barriers to equitable accessespecially for users with visual impairmentscognitive or learning disabilitiesor for anyone needing more efficient and effective ways of finding relevant information within these long documentsWe propose using AI techniquesincluding natural language processingNLPcomputer visionand text analysisto convert PDFs into machine-readable HTML documents with semantic tags and structureextracting figures and tablesand generating summaries and keywordsOur goal is to increase the accessibility of ETDs and to make this important scholarship available to a wider audienceInstificational CollectionThrough research descriptionthe universitys institutional collection system is used to managepreserve and distribute the smart achievements from faculty and studentsincluding a large number of ETDSRetrieval and IndexingBy converting PDF to HTMLand abstracts and keyword extractionit can be easier to retrieve and index ETDSThis study focuses on solving the problem of the electronic papers and papersETDSin digital librariesIn order to make ETDS more machine readability and popularityit is proposed to use AI technologyincluding natural language processingNLPcomputer vision and text analysis to convert PDFSand extract a semantic label and structureextract charts and generate abstracts And keywordsThrough further machine learning and deep learning technologiesETDS can be improved