{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:10:37Z","timestamp":1740175837533,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1005100","2018YFB1005104"],"award-info":[{"award-number":["2018YFB1005100","2018YFB1005104"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3507382","type":"journal-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:41:56Z","timestamp":1732736516000},"page":"183133-183142","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Sindhi Word Segmentation Using Subword Representation Learning and Position-Aware Self-Attention"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9392-459X","authenticated-orcid":false,"given":"Wazir","family":"Ali","sequence":"first","affiliation":[{"name":"College of Computer Science and Information Systems, Institute of Business Management, Karachi, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4915-9701","authenticated-orcid":false,"given":"Jay","family":"Kumar","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada"}]},{"given":"Saifullah","family":"Tumrani","sequence":"additional","affiliation":[{"name":"Hessianflux OÜ, Tallinn, Estonia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6030-1505","authenticated-orcid":false,"given":"Redhwan","family":"Nour","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computer Science and Engineering, Taibah University, Medina, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8251-1853","authenticated-orcid":false,"given":"Adeeb","family":"Noor","sequence":"additional","affiliation":[{"name":"Department of Information Technology, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-6461","authenticated-orcid":false,"given":"Zenglin","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"1","article-title":"Word segmentation model for Sindhi text","volume":"2","author":"Bhatti","year":"2014","journal-title":"Amer. J. Comput. Res. Repository"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2846095"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532-7078.2011.00075.x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10363"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2893460"},{"key":"ref6","first-page":"2562","article-title":"Urdu word segmentation using conditional random fields (CRFs)","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Zia"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44693-1_26"},{"key":"ref8","first-page":"279","article-title":"Long short-term memory for Japanese word segmentation","volume-title":"Proc. 32nd Pacific Asia Conf. Lang., Inf. Comput.","author":"Kitagawa"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3232537"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEECT.2017.7916560"},{"issue":"1","key":"ref11","first-page":"43","article-title":"A model for Sindhi text segmentation into word tokens","volume":"44","author":"Mahar","year":"2012","journal-title":"Sindh Univ. Res. J., Sci. Ser."},{"issue":"3","key":"ref12","article-title":"Algorithms for Sindhi word segmentation using lexicon-driven approach","volume":"3","author":"Mahar","year":"2011","journal-title":"Int. J. Academic Res."},{"issue":"2","key":"ref13","first-page":"19","article-title":"Automatic stemming and lemmatization process for Sindhi text","volume":"6","author":"Dootio","year":"2017","journal-title":"J. Social Sci. Interdiscipl. Res."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3649456"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.107921"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3395454"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1101"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3606696"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07906-x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.317"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-2008"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975738"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106548"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030487"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1141"},{"key":"ref27","first-page":"173","article-title":"Character-based joint segmentation and POS tagging for Chinese using bidirectional RNN-CRF","volume-title":"Proc. 8th Int. Joint Conf. Natural Lang. Process.","author":"Shao"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1078"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46681-1_42"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1529"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref33","first-page":"1638","article-title":"Contextual string embeddings for sequence labeling","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Akbik"},{"key":"ref34","first-page":"2023","article-title":"Task-oriented word embedding for text classification","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Liu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","volume-title":"Proc. 18th Int. Conf. Mach. Learn.","author":"Lafferty"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.7640"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICECUBE.2016.7495248"},{"key":"ref39","first-page":"39","article-title":"Towards Sindhi corpus construction","volume-title":"Proc. Conf. Lang. Technol.","author":"Rahman"},{"key":"ref40","first-page":"87","article-title":"Effective tag set selection in Chinese word segmentation via conditional random field modeling","volume-title":"Proc. 20th Pacific Asia Conf. Lang., Inf. Comput.","author":"Zhao"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3325730.3325736"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2830117"},{"key":"ref46","article-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"Huang","year":"2015","journal-title":"arXiv:1508.01991"},{"key":"ref47","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Abadi"},{"key":"ref48","article-title":"Word embedding based new corpus for low-resourced language: Sindhi","author":"Ali","year":"2019","journal-title":"arXiv:1911.12579"},{"key":"ref49","first-page":"75","article-title":"Cross-lingual word segmentation and morpheme segmentation as sequence labelling","volume-title":"Proc. 1st Workshop Multi-Lang. Process. Globalising World","author":"Shao"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1201\/9781003102670-22"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1231"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111705"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12143106"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3250241"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Kingma","key":"ref55"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10769409.pdf?arnumber=10769409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T18:49:31Z","timestamp":1740163771000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10769409\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3507382","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}