{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:55:46Z","timestamp":1780775746780,"version":"3.54.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Indonesia Endowment Fund for Education (LPDP), Ministry of Finance, Republic of Indonesia","award":["LOG-9715\/LPDP\/LPDP.3\/2024"],"award-info":[{"award-number":["LOG-9715\/LPDP\/LPDP.3\/2024"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3679735","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:13:40Z","timestamp":1775074420000},"page":"50993-51006","source":"Crossref","is-referenced-by-count":1,"title":["Efficient Transformer Models via Language-Aware Frequency-Based Vocabulary Pruning"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7595-7646","authenticated-orcid":false,"given":"Mukhlish","family":"Fuadi","sequence":"first","affiliation":[{"name":"1Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0651-5078","authenticated-orcid":false,"given":"Adhi Dharma","family":"Wibawa","sequence":"additional","affiliation":[{"name":"1Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1744-1342","authenticated-orcid":false,"given":"Surya","family":"Sumpeno","sequence":"additional","affiliation":[{"name":"1Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.189"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1493"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref5","article-title":"DeBERTaV3: Improving DeBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing","author":"He","year":"2021","journal-title":"arXiv:2111.09543"},{"key":"ref6","article-title":"MmBERT: A modern multilingual encoder with annealed language learning","author":"Marone","year":"2025","journal-title":"arXiv:2509.06888"},{"key":"ref7","article-title":"Towards greener LLMs: Bringing energy-efficiency to the forefront of LLM inference","author":"Stojkovic","year":"2024","journal-title":"arXiv:2403.20306"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ITIS59651.2023.10420049"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.ijcnlp-srw.5"},{"key":"ref10","first-page":"771","article-title":"Efficient vocabulary reduction for small language models","volume-title":"Proc. 31st Int. Conf. Comput. Linguistics, Ind. Track","author":"Nozaki"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.243"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.868"},{"key":"ref13","first-page":"10","article-title":"NusaBERT: Teaching IndoBERT to be multilingual and multicultural","volume-title":"Proc. 2nd Workshop South East Asian Lang. Process.","author":"Wongso"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.813"},{"key":"ref15","article-title":"Load what you need: Smaller versions of multilingual BERT","author":"Abdaoui","year":"2020","journal-title":"arXiv:2010.05609"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.insights-1.17"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2025.1518965"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.981"},{"key":"ref19","article-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","author":"He","year":"2020","journal-title":"arXiv:2006.03654"},{"key":"ref20","first-page":"1897","article-title":"Netguardai at exist2025: Sexism detection using mDeBERTa","volume-title":"Proc. Work. Notes Conf. Labs Eval. Forum (CLEF)","author":"Cotelin"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1086\/730737"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.835"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.ijcnlp-long.164"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.45"},{"key":"ref27","article-title":"Prune or retrain: Optimizing the vocabulary of multilingual models for Estonian","author":"Dorkin","year":"2025","journal-title":"arXiv:2501.02631"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/EEISS65394.2025.11086014"},{"key":"ref29","first-page":"645","article-title":"Vocabulary replacement in sentencepiece for domain adaptation","volume-title":"Proc. 37th Pacific Asia Conf. Lang., Inf. Comput.","author":"Kajiura"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.398"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"},{"key":"ref32","article-title":"VocabTailor: Dynamic vocabulary selection for downstream tasks in small language models","author":"Zhang","year":"2025","journal-title":"arXiv:2508.15229"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1893"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.28995\/2075-7182-2022-21-295-310"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.141"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.18"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.224"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-short.63"},{"key":"ref39","first-page":"759","article-title":"Building large monolingual dictionaries at the leipzig corpora collection: From 100 to 200 languages","volume-title":"Proc. LREC","author":"Goldhahn"},{"key":"ref40","article-title":"HuggingFace\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019","journal-title":"arXiv:1910.03771"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.57"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.85"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2018.8629158"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICAICTA.2019.8904199"},{"key":"ref45","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11460136.pdf?arnumber=11460136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:07:33Z","timestamp":1775678853000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11460136\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3679735","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}