{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:36:32Z","timestamp":1772645792922,"version":"3.50.1"},"reference-count":66,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,12,10]],"date-time":"2021-12-10T00:00:00Z","timestamp":1639094400000},"content-version":"vor","delay-in-days":343,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004194","name":"Northwest University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004194","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Mixed script identification is a hindrance for automated natural language processing systems. Mixing cursive scripts of different languages is a challenge because NLP methods like POS tagging and word sense disambiguation suffer from noisy text. This study tackles the challenge of mixed script identification for mixed\u2010code dataset consisting of Roman Urdu, Hindi, Saraiki, Bengali, and English. The language identification model is trained using word vectorization and RNN variants. Moreover, through experimental investigation, different architectures are optimized for the task associated with Long Short\u2010Term Memory (LSTM), Bidirectional LSTM, Gated Recurrent Unit (GRU), and Bidirectional Gated Recurrent Unit (Bi\u2010GRU). Experimentation achieved the highest accuracy of 90.17 for Bi\u2010GRU, applying learned word class features along with embedding with GloVe. Moreover, this study addresses the issues related to multilingual environments, such as Roman words merged with English characters, generative spellings, and phonetic typing.<\/jats:p>","DOI":"10.1155\/2021\/8415333","type":"journal-article","created":{"date-parts":[[2021,12,11]],"date-time":"2021-12-11T02:20:41Z","timestamp":1639189241000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Mixed Script Identification Using Automated DNN Hyperparameter Optimization"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6690-2555","authenticated-orcid":false,"given":"Muhammad","family":"Yasir","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9550-9779","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6929-3935","authenticated-orcid":false,"given":"Amna","family":"Khatoon","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7348-186X","authenticated-orcid":false,"given":"Muhammad Amir","family":"Malik","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3925-6180","authenticated-orcid":false,"given":"Fazeel","family":"Abid","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2021,12,10]]},"reference":[{"key":"e_1_2_10_1_2","first-page":"43","article-title":"Reasons and motivations for code-mixing and code-switching","volume":"4","author":"Kim E.","year":"2006","journal-title":"Issues EFL"},{"key":"e_1_2_10_2_2","doi-asserted-by":"crossref","unstructured":"BarmanU. DasA. WagnerJ. andFosterJ. Code mixing: a challenge for language identification in the language of social media Proceedings of the First Workshop on Computational Approaches to Code Switching October 2014 Association for Computational Linguistics Doha Qatar 13\u201323 https:\/\/doi.org\/10.3115\/v1\/w14-3902.","DOI":"10.3115\/v1\/W14-3902"},{"key":"e_1_2_10_3_2","doi-asserted-by":"crossref","unstructured":"GravesA. MohamedA.-r. andHintonG. Speech recognition with deep recurrent neural networks 3 Proceedings of the 2013 IEEE International Conference on Acoustics Speech and Signal Processing May 2013 Vancouver Canada 6645\u20136649 https:\/\/doi.org\/10.1109\/ICASSP.2013.6638947 2-s2.0-84890543083.","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"e_1_2_10_4_2","doi-asserted-by":"crossref","unstructured":"MisawaS. TaniguchiM. MiuraY. andOhkumaT. Character-based bidirectional LSTM-CRF with words and characters for Japanese named entity recognition Proceedings of the First Workshop on Subword and Character Level Models in NLP September 2017 Copenhagen Denmark 97\u2013102 https:\/\/doi.org\/10.18653\/v1\/w17-4114.","DOI":"10.18653\/v1\/W17-4114"},{"key":"e_1_2_10_5_2","unstructured":"ChungJ. GulcehreC. ChoK. andBengioY. Empirical evaluation of gated recurrent neural networks on sequence modeling Proceedings of the International Conference on Machine Learning 2014 1\u20139."},{"key":"e_1_2_10_6_2","doi-asserted-by":"crossref","unstructured":"Nussbaum-ThomM. CuiJ. RamabhadranB. andGoelV. Acoustic modeling using bidirectional gated recurrent convolutional units Proceedings of the Interspeech 2016 September 2016 390\u2013394 https:\/\/doi.org\/10.21437\/Interspeech.2016-212 2-s2.0-84994268348.","DOI":"10.21437\/Interspeech.2016-212"},{"key":"e_1_2_10_7_2","doi-asserted-by":"crossref","unstructured":"BaliK. SharmaJ. ChoudhuryM. andVyasY. I am borrowing ya mixing ? an analysis of english-hindi code mixing in facebook Proceedings of the First Workshop on Computational Approaches to Code Switching October 2014 Doha Qatar 116\u2013126 https:\/\/doi.org\/10.3115\/v1\/w14-3914.","DOI":"10.3115\/v1\/W14-3914"},{"key":"e_1_2_10_8_2","unstructured":"LuiM.andBaldwinT. langid.py: an off-the-shelf language identification tool Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics July 2012 Jeju Republic of Korea 25\u201330."},{"key":"e_1_2_10_9_2","doi-asserted-by":"publisher","DOI":"10.2307\/2802493"},{"key":"e_1_2_10_10_2","doi-asserted-by":"publisher","DOI":"10.1080\/01434632.1992.9994482"},{"key":"e_1_2_10_11_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0021937100024837"},{"key":"e_1_2_10_12_2","volume-title":"Book Reviews Duelling Languages: Grammatical Structure in Codes Witching Reviewed by: Nanda Poulisse","author":"Chapter I.","year":"1998"},{"key":"e_1_2_10_13_2","doi-asserted-by":"crossref","unstructured":"ChandaA. DasD. andMazumdarC. Unraveling the English-Bengali code-mixing phenomenon Proceedings of the Second Workshop on Computational Approaches to Code Switching November 2016 Austin TX USA 80\u201389 https:\/\/doi.org\/10.18653\/v1\/w16-5810.","DOI":"10.18653\/v1\/W16-5810"},{"key":"e_1_2_10_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-1275-9_5"},{"key":"e_1_2_10_15_2","unstructured":"SreelakshmiK.andSoman KpP. B. Amrita_CEN_NLP@DravidianLangTech-EACL2021: deep learning-based offensive language identification in Malayalam Tamil and Kannada Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages April 2021 249\u2013254."},{"key":"e_1_2_10_16_2","unstructured":"RodriguesP.andK\u00fcblerS. Part of speech tagging bilingual speech transcripts with intrasentential model switching SS-13-01 Proceedings of the AAAI Spring Symposium 2013 56\u201363."},{"key":"e_1_2_10_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(92)90019-Z"},{"key":"e_1_2_10_18_2","doi-asserted-by":"crossref","unstructured":"SolorioT.andLiuY. Part-of-speech tagging for English-Spanish code-switched text Proceedings of the Conference on Empirical Methods in Natural Language Processing - EMNLP\u201908 2008 1051\u20131060 https:\/\/doi.org\/10.3115\/1613715.1613852.","DOI":"10.3115\/1613715.1613852"},{"key":"e_1_2_10_19_2","unstructured":"DongN.andDo\u0287ru\u00f6zA. S. Word level language identification in online multilingual communication 23 Proceedings of the EMNLP 2013 - 2013 Conf. Empir. Methods Nat. Lang. Process. Proc. Conf. October 2013 Seattle WA USA 857\u2013862."},{"key":"e_1_2_10_20_2","doi-asserted-by":"crossref","unstructured":"RosnerM.andFarrugiaP. J. A tagging algorithm for mixed language identification in a noisy domain 3 Proceedings of the 8th 2007 International Speech Communication Association Annual Conference August 2007 Seattle WA USA International Speech Communication Association (ISCA) Antwerp Belgium 1941\u20131944 https:\/\/doi.org\/10.21437\/interspeech.2007-77.","DOI":"10.21437\/Interspeech.2007-77"},{"key":"e_1_2_10_21_2","unstructured":"VossC. TratzS. LaoudiJ. andBrieschD. Finding romanized Arabic dialect in code-mixed tweets Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014) 2014 Doha Qatar 2249\u20132253."},{"key":"e_1_2_10_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38824-8_51"},{"key":"e_1_2_10_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-015-9303-x"},{"key":"e_1_2_10_24_2","unstructured":"LiY. YuY. andFungP. A Mandarin-English code-switching corpus Proceedings of the 8th Conference on Language Resources and Evaluation (LREC012) 2012 Lid 2515\u20132519."},{"key":"e_1_2_10_25_2","doi-asserted-by":"crossref","unstructured":"YeongY.-L.andTanT.-P. Applying grapheme word and syllable information for language identification in code switching sentences Proceedings of the 2011 International Conference on Asian Language Processing 2011 Penang Malaysia 111\u2013114 https:\/\/doi.org\/10.1109\/IALP.2011.34 2-s2.0-84856033836.","DOI":"10.1109\/IALP.2011.34"},{"key":"e_1_2_10_26_2","unstructured":"BalazevicI. BraunM. andM\u00fcllerK.-R. Language detection for short text messages in social media 2016 https:\/\/arxiv.org\/abs\/1608.08515."},{"key":"e_1_2_10_27_2","unstructured":"DasA.andGamb\u00e4ckB. Identifying languages at the word level in code-mixed Indian social media text Proceedings of the 11th International Conference on Natural Language Processing 2014 169\u2013178."},{"key":"e_1_2_10_28_2","doi-asserted-by":"crossref","unstructured":"BarmanU. WagnerJ. Chrupa\u0142aG. andFosterJ. DCU-UVT: word-level language classification with code-mixed data Proceedings of the First Workshop on Computational Approaches to Code Switching October 2014 Association for Computational Linguistics Doha Qatar 127\u2013132 https:\/\/doi.org\/10.3115\/v1\/w14-3915.","DOI":"10.3115\/v1\/W14-3915"},{"key":"e_1_2_10_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2018.09.009"},{"key":"e_1_2_10_30_2","doi-asserted-by":"crossref","unstructured":"SamihY. MaharjanS. AttiaM. KallmeyerL. andSolorioT. Multilingual code-switching identification via LSTM recurrent neural networks Proceedings of the Second Workshop on Computational Approaches to Code Switching November 2016 Association for Computational Linguistics Austin TX USA 50\u201359 https:\/\/doi.org\/10.18653\/v1\/w16-5806.","DOI":"10.18653\/v1\/W16-5806"},{"key":"e_1_2_10_31_2","doi-asserted-by":"crossref","unstructured":"SinghK. SenI. andKumaraguruP. language identification and named entity recognition in hinglish code mixed tweets Proceedings of ACL 2018 Student Research Workshop July 2018 Association for Computational Linguistics Melbourne Australia 52\u201358 https:\/\/doi.org\/10.18653\/v1\/p18-3008.","DOI":"10.18653\/v1\/P18-3008"},{"key":"e_1_2_10_32_2","unstructured":"GuptaD. Shweta TripathiS. EkbalA. andBhattacharyyaP. A hybrid approach for entity extraction in code-mixed social media data 1737 Proceedings of the CEUR Workshop 2016 298\u2013303."},{"key":"e_1_2_10_33_2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/2195922"},{"key":"e_1_2_10_34_2","doi-asserted-by":"crossref","unstructured":"AbuhamadM. AbuHmedT. MohaisenA. andNyangD. Large-scale and language-oblivious code authorship identification Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security October 2018 Toronto Canada 101\u2013114 https:\/\/doi.org\/10.1145\/3243734.3243738 2-s2.0-85056906258.","DOI":"10.1145\/3243734.3243738"},{"key":"e_1_2_10_35_2","doi-asserted-by":"crossref","unstructured":"MaveD. MaharjanS. andSolorioT. language identification and analysis of code-switched social media text Proceedings of the Third Workshop on Computational Approaches to Code-Switching Association for Computational Linguistics July 2018 Melbourne Australia 51\u201361 https:\/\/doi.org\/10.18653\/v1\/w18-3206.","DOI":"10.18653\/v1\/W18-3206"},{"key":"e_1_2_10_36_2","doi-asserted-by":"crossref","unstructured":"PenningtonJ. SocherR. andManningC. D. GloVe: Global Vectors for Word Representation Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) October 2014 Association for Computational Linguistics Doha Qatar 1532\u20131543.","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_2_10_37_2","doi-asserted-by":"publisher","DOI":"10.1108\/AJIM-04-2018-0091"},{"key":"e_1_2_10_38_2","doi-asserted-by":"crossref","unstructured":"SolorioT. BlairE. MaharjanS. BethardS. DiabM. GhoneimM. HawwariA. AlGhamdiF. HirschbergJ. ChangA. andFungP. Overview for the first shared task on language identification in code-switched data Proceedings of the First Workshop on Computational Approaches to Code Switching October 2014 Association for Computational Linguistics Doha Qatar 62\u201372 https:\/\/doi.org\/10.3115\/v1\/w14-3907.","DOI":"10.3115\/v1\/W14-3907"},{"key":"e_1_2_10_39_2","doi-asserted-by":"publisher","DOI":"10.1515\/jisys-2017-0440"},{"key":"e_1_2_10_40_2","unstructured":"Twitter Natural Language Processing-Noah\u2019s ARK 2021 http:\/\/www.cs.cmu.edu\/\u223cark\/TweetNLP\/."},{"key":"e_1_2_10_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/505282.505283"},{"key":"e_1_2_10_42_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_10_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"e_1_2_10_44_2","doi-asserted-by":"crossref","unstructured":"DeyR.andSalemF. M. Gate-variants of gated recurrent unit (GRU) 2017 784.","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"e_1_2_10_45_2","doi-asserted-by":"crossref","unstructured":"KhanS. A. KhalidS. M. D. ShahzadM. A. andShafaitF. Table structure extraction with bi-directional gated recurrent unit networks Proceedings of the 2019 International Conference on Document Analysis and Recognition (ICDAR) September 2019 Sydney Australia 1366\u20131371 https:\/\/doi.org\/10.1109\/ICDAR.2019.00220.","DOI":"10.1109\/ICDAR.2019.00220"},{"key":"e_1_2_10_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2020.100591"},{"key":"e_1_2_10_47_2","unstructured":"BergstraJ. BardenetR. K\u00e9glB. andBengioY. Implementations of algorithms for hyper-parameter optimization 29 Proceedings of the NIPS Workshop Bayesian Optim. 2011."},{"key":"e_1_2_10_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2020.3039072"},{"key":"e_1_2_10_49_2","unstructured":"DillonJ. V. LangmoreI. TranD. BrevdoE. VasudevanS. MooreD. PattonB. AlemiA. HoffmanM. andSaurousR. A. Tensorflow distributions 2017 http:\/\/arxiv.org\/abs\/1711.10604."},{"key":"e_1_2_10_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.12.018"},{"key":"e_1_2_10_51_2","unstructured":"QuY. LiuJ. KangL. ShiQ. andYeD. Question answering over freebase via attentive RNN with similarity matrix based CNN 2018 https:\/\/arxiv.org\/vc\/arxiv\/papers\/1804\/1804.03317v2.pdf."},{"key":"e_1_2_10_52_2","doi-asserted-by":"crossref","unstructured":"LiuC. WangY. KumarK. andGongY. Investigations on speaker adaptation of LSTM RNN models for speech recognition Proceedings of the 2016 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) May 2016 Shanghai China 5020\u20135024 https:\/\/doi.org\/10.1109\/ICASSP.2016.7472633 2-s2.0-84973400139.","DOI":"10.1109\/ICASSP.2016.7472633"},{"key":"e_1_2_10_53_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"e_1_2_10_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.137"},{"key":"e_1_2_10_55_2","doi-asserted-by":"crossref","unstructured":"LiS. WuC. LiH. LiB. WangY. andQiuQ. FPGA acceleration of recurrent neural network based language model Proceedings of the 2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines 2015 Vancouver Canada 111\u2013118 https:\/\/doi.org\/10.1109\/FCCM.2015.50 2-s2.0-84943378851.","DOI":"10.1109\/FCCM.2015.50"},{"key":"e_1_2_10_56_2","unstructured":"HansK.andMiltonR. S. Improving the performance of neural machine translation involving morphologically rich languages 2016 https:\/\/arxiv.org\/abs\/1612.02482."},{"key":"e_1_2_10_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jare.2020.04.006"},{"key":"e_1_2_10_58_2","doi-asserted-by":"publisher","DOI":"10.3390\/e17107185"},{"key":"e_1_2_10_59_2","doi-asserted-by":"publisher","DOI":"10.1142\/S0218488598000094"},{"key":"e_1_2_10_60_2","doi-asserted-by":"crossref","unstructured":"RayA. RajeswarS. andChaudhuryS. Text recognition using deep BLSTM networks Proceedings of the 2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR) January 2015 Kolkata India https:\/\/doi.org\/10.1109\/ICAPR.2015.7050699 2-s2.0-84925624580.","DOI":"10.1109\/ICAPR.2015.7050699"},{"key":"e_1_2_10_61_2","doi-asserted-by":"crossref","unstructured":"MaC. YangC. YangF. ZhuangY. ZhangZ. JiaH. andXieX. Trajectory factory: tracklet cleaving and Re-connection by deep siamese Bi-GRU for multiple object tracking Proceedings of the 2018 IEEE International Conference on Multimedia and Expo (ICME) July 2018 San Diego CA USA https:\/\/doi.org\/10.1109\/ICME.2018.8486454 2-s2.0-85059827574.","DOI":"10.1109\/ICME.2018.8486454"},{"key":"e_1_2_10_62_2","doi-asserted-by":"crossref","unstructured":"LinB. Y. XuF. LuoZ. andZhuK. Multi-channel BiLSTM-CRF model for emerging named entity recognition in social media Proceedings of the 3rd Workshop on Noisy User-generated Text 2017 160\u2013165 https:\/\/doi.org\/10.18653\/v1\/w17-4421.","DOI":"10.18653\/v1\/W17-4421"},{"key":"e_1_2_10_63_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46681-1_42"},{"key":"e_1_2_10_64_2","volume-title":"1986 - Unknown - \u00a9 1986","author":"Robertson","year":"1986"},{"key":"e_1_2_10_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"e_1_2_10_66_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.12.038"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/8415333.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/8415333.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/8415333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T12:30:29Z","timestamp":1722947429000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/8415333"}},"subtitle":[],"editor":[{"given":"Ahmed Mostafa","family":"Khalil","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":66,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/8415333"],"URL":"https:\/\/doi.org\/10.1155\/2021\/8415333","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"value":"1687-5265","type":"print"},{"value":"1687-5273","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-10-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8415333"}}