{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T07:26:22Z","timestamp":1781940382456,"version":"3.54.5"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012190","name":"Ministry of Science and Higher Education of the Russian Federation","doi-asserted-by":"publisher","award":["075-10-2021-068"],"award-info":[{"award-number":["075-10-2021-068"]}],"id":[{"id":"10.13039\/501100012190","id-type":"DOI","asserted-by":"publisher"}]},{"name":"framework of the HSE University Basic Research Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3169897","type":"journal-article","created":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T19:34:23Z","timestamp":1650656063000},"page":"45736-45747","source":"Crossref","is-referenced-by-count":72,"title":["NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5065-4000","authenticated-orcid":false,"given":"Nikita","family":"Klyuchnikov","sequence":"first","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilya","family":"Trofimov","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8689-7514","authenticated-orcid":false,"given":"Ekaterina","family":"Artemova","sequence":"additional","affiliation":[{"name":"Models and methods for computational pragmatics Laboratory, Higher School of Economics University, Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8865-6677","authenticated-orcid":false,"given":"Mikhail","family":"Salnikov","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maxim","family":"Fedorov","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9826-2425","authenticated-orcid":false,"given":"Alexander","family":"Filippov","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8424-0690","authenticated-orcid":false,"given":"Evgeny","family":"Burnaev","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1740\/1\/012050"},{"key":"ref2","first-page":"1","article-title":"NAS evaluation is frustratingly hard","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref3","first-page":"367","article-title":"Random search and reproducibility for neural architecture search","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Li"},{"issue":"243","key":"ref4","first-page":"1","article-title":"Best practices for scientific research on neural architecture search","volume":"21","author":"Lindauer","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","first-page":"7105","article-title":"NAS-bench-101: Towards reproducible neural architecture search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ying"},{"key":"ref6","first-page":"1","article-title":"NAS-bench-201: Extending the scope of reproducible neural architecture search","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dong"},{"key":"ref7","article-title":"Multiplicative LSTM for sequence modelling","author":"Krause","year":"2016","journal-title":"arXiv:1609.07959"},{"key":"ref8","first-page":"1","article-title":"Mogrifier LSTM","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Melis"},{"key":"ref9","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013159"},{"key":"ref11","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"Bengio","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","article-title":"Exploring the limits of language modeling","author":"Jozefowicz","year":"2016","journal-title":"arXiv:1602.02410"},{"key":"ref13","first-page":"4189","article-title":"Recurrent highway networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Zilly"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1151"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/621"},{"key":"ref19","first-page":"4906","article-title":"Densely connected attention propagation for reading comprehension","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tay"},{"key":"ref20","article-title":"Tabular benchmarks for joint architecture and hyperparameter optimization","author":"Klein","year":"2019","journal-title":"arXiv:1905.04970"},{"key":"ref21","first-page":"1","article-title":"NAS-bench-1shot1: Benchmarking and dissecting one-shot neural architecture search","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zela"},{"key":"ref22","article-title":"Surrogate NAS benchmarks: Going beyond the limited search spaces of tabular NAS benchmarks","author":"Zela","year":"2020","journal-title":"arXiv:2008.09777"},{"key":"ref23","first-page":"1","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref25","first-page":"2342","article-title":"An empirical exploration of recurrent network architectures","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jozefowicz"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref28","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016","journal-title":"arXiv:1611.01578"},{"key":"ref29","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. ICML","author":"Pham"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.insights-1.4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1367"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.592"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6462"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467262"},{"key":"ref35","first-page":"5877","article-title":"The evolved transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"So"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref38","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv:1609.07843"},{"key":"ref39","first-page":"1","article-title":"Regularizing and optimizing LSTM language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Merity"},{"key":"ref40","volume-title":"LSTM and QRNN Language Model Toolkit","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5220\/0005209202710278"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.25080\/TCWV9851","article-title":"Exploring network structure, dynamics, and function using networkX","author":"Hagberg","year":"2008"},{"key":"ref43","article-title":"Graph2vec: Learning distributed representations of graphs","author":"Narayanan","year":"2017","journal-title":"arXiv:1707.05005"},{"key":"ref44","article-title":"A tutorial on Bayesian optimization","author":"Frazier","year":"2018","journal-title":"arXiv:1807.02811"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref46","volume-title":"WikiExtractor","author":"Attardi","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1036"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1023"},{"key":"ref50","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mikolov"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372094"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00237"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref54","volume-title":"jiant 1.3: A software toolkit for research on general-purpose text understanding models","author":"Wang","year":"2019"},{"issue":"1","key":"ref55","first-page":"6765","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","volume":"18","author":"Li","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref57","first-page":"115","article-title":"Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Bergstra"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"ref59","first-page":"2016","article-title":"Neural architecture search with Bayesian optimisation and optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kandasamy"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17233"},{"key":"ref61","article-title":"Local search is state of the art for NAS benchmarks","author":"White","year":"2020","journal-title":"arXiv:2005.02960"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09762315.pdf?arnumber=9762315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T20:13:51Z","timestamp":1727036031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9762315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3169897","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}