{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:54:06Z","timestamp":1730256846769,"version":"3.28.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T00:00:00Z","timestamp":1692921600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T00:00:00Z","timestamp":1692921600000},"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":[[2023,8,25]]},"DOI":"10.1109\/icsecs58457.2023.10256423","type":"proceedings-article","created":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T17:36:02Z","timestamp":1695749762000},"page":"89-95","source":"Crossref","is-referenced-by-count":1,"title":["An Overview of Part-of-Speech Tagging Methods and Datasets for Malay Language"],"prefix":"10.1109","author":[{"given":"Chi Log","family":"Chua","sequence":"first","affiliation":[{"name":"Tunku Abdul Rahman University of Management and Technology (TAR UMT),Faculty of Computing And Information Technology (FOCS),Kuala Lumpur,Malaysia"}]},{"given":"Tong Ming","family":"Lim","sequence":"additional","affiliation":[{"name":"Centre For Business Incubation And Entrepreneurial Ventures (CBIEV) Tunku Abdul Rahman University of Management and Technology (TAR UMT),Kuala Lumpur,Malaysia"}]},{"given":"Kwee Teck","family":"See","sequence":"additional","affiliation":[{"name":"Tunku Abdul Rahman University of Management and Technology (TAR UMT),Faculty of Computing And Information Technology (FOCS),Kuala Lumpur,Malaysia"}]}],"member":"263","reference":[{"journal-title":"(accessed","article-title":"msTenTen - Malay corpus from the web - Sketch Engine","year":"2023","key":"ref13"},{"journal-title":"(accessed","article-title":"Malay text corpora - Sketch Engine","year":"2023","key":"ref12"},{"journal-title":"OpenSubtitles parallel corpora - Sketch Engine","year":"0","key":"ref15"},{"journal-title":"(accessed","article-title":"MalaysianWaC - Malaysian corpus from the web - Sketch Engine","year":"2023","key":"ref14"},{"key":"ref53","first-page":"160","article-title":"POS Tagging Model for Malay Tweets Using New POS Tagset and BiLTSM-CRF Approach","author":"tiun","year":"2022","journal-title":"ALTNLP The International Conference and workshop on Agglutinative Language Technologies as a challenge of Natural Language Processing V Jernej and Branko Kavšek Eds Koper CEUR Workshop Proceedings"},{"key":"ref52","first-page":"79","article-title":"Evaluating LSTM Networks, HMM and WFST in Malay Part-of-Speech Tagging","volume":"9","author":"tan","year":"2017","journal-title":"Journal of Telecommunication Electronic and Computer Engineering (JTEC)"},{"journal-title":"(accessed","article-title":"Word databases, language tools and solutions - Lexical Computing","year":"2023","key":"ref11"},{"journal-title":"(accessed","article-title":"GitHub - UniversaIDependencies\/UD_Indonesian-GSD: Indonesian conversion","year":"2023","key":"ref10"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2020.0111021"},{"journal-title":"Building a Large Annotated Corpus of English The Penn Treebank","year":"0","key":"ref17"},{"journal-title":"Comparison of Treebank Statistics","year":"0","key":"ref16"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.4324\/9781315815879"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.4324\/9780203821121"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11010056"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4808"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101138"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/UBMK.2018.8566272"},{"key":"ref48","article-title":"Part-of-Speech Tagging for Arabic Gulf Dialect Using Bi-LSTM","author":"alharbi","year":"0","journal-title":"Accessed May 10 2023 [Online] Available"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-020-09716-9"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2022.0130730"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.17576\/gema-2018-1804-09"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT45670.2019.8944559"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref49","first-page":"193","article-title":"Transformer-based Part-of-Speech Tagging and Lemmatization for Latin","author":"wr\u00f2bel","year":"2022","journal-title":"Accessed May 10 2023 [Online] Available"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2020.07.011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24297\/jal.v12i.9122"},{"key":"ref9","article-title":"OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles","author":"lison","year":"0","journal-title":"Accessed May 10 2023 [Online] Available"},{"key":"ref4","article-title":"English News Text Treebank: Penn Treebank Revised","author":"bies","year":"2015","journal-title":"Philadelphia Linguistic Data Consortium"},{"key":"ref3","article-title":"The Austronesian languages. Asia-Pacific Linguistics, School of Culture, History and Language, College of Asia and the Pacific","author":"blust","year":"0","journal-title":"The Australian National University 2013 Accessed May 09 2023 [Online] Available"},{"journal-title":"(accessed","article-title":"chinese-corpus. GitHub Topics. GitHub","year":"2023","key":"ref6"},{"key":"ref5","article-title":"A Gold Standard Dependency Corpus for English","author":"silveira","year":"0","journal-title":"Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC-2014)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18178\/ijke.2016.2.3.064"},{"journal-title":"A Maximum Entropy Model for Part-of-Speech Tagging","year":"0","author":"ratnaparkhi","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75171-7_2"},{"journal-title":"Unknown Word Guessing and Part-of-Speech Tagging Using Support Vector Machines","year":"0","author":"nakagawa","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(92)90019-Z"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-36543-0_6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5070\/H913224023"},{"key":"ref33","article-title":"Chapter 1: The Machine Learning Landscape","author":"g\u00e9ron","year":"2017","journal-title":"Hands-On Machine Learning with Scikit-Learn Keras and TensorFlow"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.17576\/apjitm-2017-0602-09"},{"key":"ref2","article-title":"Low-resource Languages: A Review of Past Work and Future Challenges","author":"magueresse","year":"2020","journal-title":"arXiv org Cornell University Library arXiv org Ithaca"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-022-00561-y"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5220\/0005150602320240"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/STAIR.2011.5995794"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/4284.4286"},{"key":"ref23","first-page":"4003","article-title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","author":"wenzek","year":"2020","journal-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference Marseille France European Language Resources Association"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2014.6973521"},{"journal-title":"A Simple Rule-Based Part of Speech Tagger","year":"0","author":"brill","key":"ref25"},{"key":"ref20","article-title":"Kesenjangan leksikal bahasa Melayu Malaysia dan bahasa Indonesia","author":"ahmad","year":"0","journal-title":"Dewan Bahasa dan Pustaka 2011 [Online] Available"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref21","article-title":"Malay-Dataset, We gather Bahasa Malaysia corpus!","author":"husein","year":"0","journal-title":"GitHub repository 2018 Accessed May 10 2023 [Online] Available"},{"key":"ref28","first-page":"163","author":"garg","year":"2012","journal-title":"Rule Based Hindi Part of Speech Tagger"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/407\/1\/012151"},{"key":"ref29","first-page":"975","article-title":"Part of Speech Tagging in Manipuri: A Rule-based Approach","volume":"51","author":"raju singha","year":"2012","journal-title":"Int J Comput Appl"}],"event":{"name":"2023 IEEE 8th International Conference On Software Engineering and Computer Systems (ICSECS)","start":{"date-parts":[[2023,8,25]]},"location":"Penang, Malaysia","end":{"date-parts":[[2023,8,27]]}},"container-title":["2023 IEEE 8th International Conference On Software Engineering and Computer Systems (ICSECS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10256260\/10256269\/10256423.pdf?arnumber=10256423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T17:51:51Z","timestamp":1697478711000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10256423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,25]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icsecs58457.2023.10256423","relation":{},"subject":[],"published":{"date-parts":[[2023,8,25]]}}}