{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:27:13Z","timestamp":1738128433145,"version":"3.33.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848851","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["GVDIE: A Zero-Shot Generative Information Extraction Method for Visual Documents Based on Large Language Models"],"prefix":"10.1109","author":[{"given":"Siyang","family":"Qi","sequence":"first","affiliation":[{"name":"State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongzhi","family":"Sun","sequence":"additional","affiliation":[{"name":"State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Ge","sequence":"additional","affiliation":[{"name":"State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xiao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Document ai: Benchmarks, models and applications","year":"2021","author":"Cui","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511709333"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00211"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.846"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.274"},{"key":"ref10","first-page":"1877","article-title":"Language models are few-shot learners[J]","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Finetuned Language Models are Zero-Shot Learners[C]","volume-title":"International Conference on Learning Representations","author":"Wei","key":"ref11"},{"journal-title":"A survey on recent advances in named entity recognition[J]","year":"2024","author":"Keraghel","key":"ref12"},{"issue":"5","key":"ref13","volume":"2","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"ref15","first-page":"36","article-title":"Lift yourself up: Retrieval-augmented text generation with self-memory[J]","author":"Cheng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Pp-ocr: A practical ultra lightweight ocr system[J]","year":"2020","author":"Du","key":"ref16"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models[J]","year":"2023","author":"Touvron","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"article-title":"{CORD}: A consolidated receipt dataset for post-{ocr} parsing","volume-title":"Workshop on Document Intelligence at NeurIPS 2019","author":"Park","key":"ref21"},{"article-title":"Qwen technical report[J]","year":"2023","author":"Bai","key":"ref22"},{"volume-title":"Internlm: A multilingual language model with progressively enhanced capabilities[J]","year":"2023","key":"ref23"},{"key":"ref24","first-page":"36","article-title":"Visual instruction tuning[J]","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848851.pdf?arnumber=10848851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:06:00Z","timestamp":1738044360000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848851","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}