{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:16:40Z","timestamp":1780327000291,"version":"3.54.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100013375","name":"Lembaga Penelitian Universitas Sumatera Utara","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013375","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Grant TALENTA USU, in 2020"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3128439","type":"journal-article","created":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T20:31:06Z","timestamp":1637094666000},"page":"155699-155710","source":"Crossref","is-referenced-by-count":13,"title":["Morpheme Embedding for Bahasa Indonesia Using Modified Byte Pair Encoding"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0595-8296","authenticated-orcid":false,"given":"Amalia","family":"Amalia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6069-1841","authenticated-orcid":false,"given":"Opim Salim","family":"Sitompul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teddy","family":"Mantoro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6368-5997","authenticated-orcid":false,"given":"Erna Budhiarti","family":"Nababan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","author":"moeliono","year":"1988","journal-title":"Tata Bahasa Baku Bahasa Indonesia (The Standard Indonesian Grammar)"},{"key":"ref38","first-page":"33","article-title":"Stemming in-donesian: A confix-stripping approach","volume":"6","author":"adriani","year":"2007","journal-title":"Journal of Educational Resources in Computing"},{"key":"ref33","article-title":"Portuguese word embeddings: Evaluating on word analogies and natural language tasks","author":"hartmann","year":"2017","journal-title":"arXiv cs\/1708 06025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.10.463"},{"key":"ref31","first-page":"53","article-title":"Finding better subword segmentation","volume":"2","author":"wu","year":"2018","journal-title":"Comput Linguist Chinese Lang Process"},{"key":"ref30","first-page":"2989","article-title":"BPEMB: Tokenization-free pre-trained subword embeddings in 275 languages","author":"heinzerling","year":"2019","journal-title":"Proc 11st Int Conf Lang Resour Eval"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2067"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1156"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5220\/0006729606630674"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1140"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.concog.2017.09.004"},{"key":"ref40","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume":"1","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","first-page":"508","article-title":"Optimizing corpus creation for training word embedding in low resource domains: A case study in autism spectrum disorder (ASD)","author":"gu","year":"2018","journal-title":"Proc AMIA Symp"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1226"},{"key":"ref13","article-title":"Which encoding is the best for text classification in Chinese, English, Japanese and Korean?","author":"zhang","year":"2017","journal-title":"arXiv 1708 02657"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref16","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv cs\/1301 3781"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2922537"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref28","first-page":"23","article-title":"A new algorithm for data compression","volume":"12","author":"gage","year":"1994","journal-title":"C Users J"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2131"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1515\/pralin-2017-0031"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1161"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/1536383X.2018.1448388"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref8","first-page":"104","article-title":"Better word representations with recursive neural networks for morphology","author":"luong","year":"2013","journal-title":"Proc 17th Conf Comput Natural Lang Learn"},{"key":"ref7","article-title":"Implicitly incorporating morphological information into word embedding","author":"xu","year":"2017","journal-title":"arXiv 1701 02481"},{"key":"ref2","first-page":"201","article-title":"Why does unsupervised pre-training help deep learning?","volume":"9","author":"erhan","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref9","first-page":"1","article-title":"Bigger does not mean better! We prefer specificity","author":"dusserre","year":"2017","journal-title":"Proc 12nd Int Conf Comput Semantics (IWCS)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00311"},{"key":"ref20","article-title":"BPE-dropout: Simple and effective subword regularization","author":"provilkov","year":"2019","journal-title":"arXiv 1910 13267"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1097"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.414"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K15-1017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-2002"},{"key":"ref23","author":"fromkin","year":"2018","journal-title":"An Introduction to Language"},{"key":"ref26","article-title":"Unsupervised morpheme segmentation and morphology induction from text corpora using morfessor 1.0","author":"creutz","year":"2005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1187415.1187418"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09615151.pdf?arnumber=9615151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,8]],"date-time":"2022-03-08T21:53:12Z","timestamp":1646776392000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9615151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3128439","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}