{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T02:45:10Z","timestamp":1775097910742,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000208","name":"Institute of Museum and Library Services","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000208","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825418","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"2400-2409","source":"Crossref","is-referenced-by-count":2,"title":["Automating Chapter-Level Classification for Electronic Theses and Dissertations"],"prefix":"10.1109","author":[{"given":"Bipasha","family":"Banerjee","sequence":"first","affiliation":[{"name":"University Libraries Virginia Tech,Blacksburg,VA,24061"}]},{"given":"William A.","family":"Ingram","sequence":"additional","affiliation":[{"name":"University Libraries Virginia Tech,Blacksburg,VA,24061"}]},{"given":"Edward A.","family":"Fox","sequence":"additional","affiliation":[{"name":"Virginia Tech,Dept. of Computer Science,Blacksburg,VA,24061"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL57899.2023.00012"},{"key":"ref2","first-page":"17","article-title":"What is Past is Prologue: A History of Archival Ideas Since 1898, and the Future Paradigm Shift","volume-title":"Archivaria","author":"Cook","year":"1997"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/asi.23099"},{"issue":"2","key":"ref4","first-page":"84","article-title":"Research data management services in academic research libraries and perceptions of librarians","volume-title":"Library & Information Science Research","volume":"36","author":"Tenopir","year":"2014"},{"key":"ref5","article-title":"Language Models are Unsupervised Multitask Learners","author":"Radford","year":"2019"},{"key":"ref6","volume-title":"Introducing ChatGPT"},{"key":"ref7","article-title":"A Neural Probabilistic Language Model","volume-title":"Advances in Neural Information Processing Systems","volume":"13","author":"Bengio","year":"2000"},{"key":"ref8","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref9","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin"},{"key":"ref10","first-page":"3615","article-title":"SciBERT: A pretrained language model for scientific text","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Beltagy"},{"key":"ref11","article-title":"Roberta: A robustly optimized bert pretraining approach","volume":"abs\/1907.11692","author":"Liu","year":"2019"},{"key":"ref12","article-title":"Big bird: Transformers for longer sequences","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020","author":"Zaheer"},{"key":"ref13","article-title":"Longformer: The Long-Document Transformer","author":"Beltagy","year":"2020"},{"key":"ref14","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref15","article-title":"Llama 3 model card","year":"2024"},{"key":"ref16","article-title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","author":"Abdin","year":"2024"},{"key":"ref17","article-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"ref18","article-title":"Claude 2","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130401"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1023\/a:1010933404324"},{"key":"ref21","article-title":"Increasing Accessibility of Electronic Theses and Dissertations (ETDs) Through Chapter-level Classification","volume-title":"VTechWorks; VT MS Thesis","author":"Jude","year":"2020"},{"key":"ref22","article-title":"Subject Categories 2019-2020 Academic Year","year":"2002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/bigdata55660.2022.10020935"},{"key":"ref24","article-title":"Improving Access to ETD Elements Through Chapter Categorization and Summarization","author":"Banerjee","year":"2024"},{"key":"ref25","volume-title":"What Is Instruction Tuning? | IBM","year":"2024"},{"key":"ref26","article-title":"Language Models are Few-Shot Learners","author":"Brown","year":"2020"},{"key":"ref27","article-title":"Understanding Zero-Shot Learning \u2014 Making ML More Human","author":"Tiu","year":"2021"},{"key":"ref28","article-title":"Zero-shot learning through cross-modal transfer","volume-title":"Advances in Neural Information Processing Systems","volume":"26","author":"Socher","year":"2013"},{"key":"ref29","article-title":"Prototypical Networks for Few-shot Learning","author":"Snell","year":"2017"},{"key":"ref30","article-title":"Meta-Learning for Semi-Supervised Few-Shot Classification","author":"Ren","year":"2018"},{"key":"ref31","article-title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","author":"Wei","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.148.3.6878708"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1161\/circulationaha.106.672402"},{"issue":"7","key":"ref34","first-page":"1145","article-title":"The use of the area under the ROC curve in the evaluation of machine learning algorithms","volume-title":"Pattern Recognition","volume":"30","author":"Bradley","year":"1997"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9672058"},{"key":"ref36","article-title":"OCR Software, Data Extraction Tool - Amazon Textract - AWS","year":"2019"},{"key":"ref37","first-page":"121","article-title":"Parsing Electronic Theses and Dissertations Using Object Detection","volume-title":"Proceedings of the first Workshop on Information Extraction from Scientific Publications","author":"Ahuja"},{"key":"ref38","article-title":"Segmenting Electronic Theses and Dissertations By Chapters","volume-title":"Thesis","author":"Manzoor","year":"2023"},{"key":"ref39","article-title":"Advanced Research Computing","year":"2024"},{"key":"ref40","article-title":"meta-llama\/Llama-2-13b-hf \u2022 Hugging Face","year":"2023"},{"key":"ref41","article-title":"meta-llama\/Meta-Llama-3-8B-Instruct \u2022 Hugging Face","year":"2024"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1410","article-title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing","author":"Reimers"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","location":"Washington, DC, USA","start":{"date-parts":[[2024,12,15]]},"end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825418.pdf?arnumber=10825418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:55:40Z","timestamp":1737100540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825418\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825418","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}