{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:06:06Z","timestamp":1776441966997,"version":"3.51.2"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s10115-022-01698-1","type":"journal-article","created":{"date-parts":[[2022,7,2]],"date-time":"2022-07-02T05:02:31Z","timestamp":1656738151000},"page":"1937-1966","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Adapter-based fine-tuning of pre-trained multilingual language models for code-mixed and code-switched text classification"],"prefix":"10.1007","volume":"64","author":[{"given":"Himashi","family":"Rathnayake","sequence":"first","affiliation":[]},{"given":"Janani","family":"Sumanapala","sequence":"additional","affiliation":[]},{"given":"Raveesha","family":"Rukshani","sequence":"additional","affiliation":[]},{"given":"Surangika","family":"Ranathunga","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,7,2]]},"reference":[{"key":"1698_CR1","unstructured":"Aguilar G, Kar S, Solorio T (2020) Lince: a centralized benchmark for linguistic code-switching evaluation. In: Proceedings of the 12th language resources and evaluation conference, pp 1803\u20131813"},{"key":"1698_CR2","doi-asserted-by":"crossref","unstructured":"Ansari MZ, Beg M, Ahmad T, et\u00a0al (2021) Language identification of Hindi-English tweets using code-mixed Bert. arXiv preprint arXiv:2107.01202","DOI":"10.1109\/ICCICC53683.2021.9811292"},{"key":"1698_CR3","doi-asserted-by":"crossref","unstructured":"Antoun W, Baly F, Achour R, et\u00a0al (2020) State of the art models for fake news detection tasks. In: 2020 IEEE international conference on informatics, IoT, and enabling technologies (ICIoT). IEEE, pp 519\u2013524","DOI":"10.1109\/ICIoT48696.2020.9089487"},{"key":"1698_CR4","first-page":"36","volume":"2018","author":"A Bohra","year":"2018","unstructured":"Bohra A, Vijay D, Singh V et al (2018) A dataset of Hindi-English code-mixed social media text for hate speech detection. NAACL HLT 2018:36","journal-title":"NAACL HLT"},{"key":"1698_CR5","unstructured":"Chakravarthi BR, Jose N, Suryawanshi S, et\u00a0al (2020) A sentiment analysis dataset for code-mixed Malayalam-English. In: Proceedings of the 1st Joint workshop on spoken language technologies for under-resourced languages (SLTU) and collaboration and computing for under-resourced languages (CCURL), pp 177\u2013184"},{"key":"1698_CR6","doi-asserted-by":"crossref","unstructured":"Chakravarthi BR, Priyadharshini R, Muralidaran V, et\u00a0al (2022) Dravidiancodemix: sentiment analysis and offensive language identification dataset for Dravidian languages in code-mixed text. Language Resources and Evaluation pp 1\u201342","DOI":"10.1007\/s10579-022-09583-7"},{"key":"1698_CR7","doi-asserted-by":"crossref","unstructured":"Chathuranga S, Ranathunga S (2021) Classification of code-mixed text using capsule networks. In: Proceedings of the international conference on recent advances in natural language processing (RANLP 2021), pp 256\u2013263","DOI":"10.26615\/978-954-452-072-4_030"},{"key":"1698_CR8","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO et al (2002) Smote: synthetic minority over-sampling technique. J Artif Intel Res 16:321\u2013357","journal-title":"J Artif Intel Res"},{"key":"1698_CR9","doi-asserted-by":"crossref","unstructured":"Conneau A, Khandelwal K, Goyal N, et\u00a0al (2020) Unsupervised cross-lingual representation learning at scale. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 8440\u20138451","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"1698_CR10","unstructured":"Das A, Gamb\u00e4ck B (2014) Identifying languages at the word level in code-mixed indian social media text. In: Proceedings of the 11th international conference on natural language processing, pp 378\u2013387"},{"key":"1698_CR11","unstructured":"Dhananjaya V, Demotte P, Ranathunga S, et\u00a0al (2022) Bertifying sinhala - a comprehensive analysis of pre-trained language models for sinhala text classification. In: Proceedings of the 13th language resources and evaluation conference"},{"key":"1698_CR12","doi-asserted-by":"crossref","unstructured":"Friedman D, Dodge B, Chen D (2021) Single-dataset experts for multi-dataset question answering. In: Proceedings of the 2021 conference on empirical methods in natural language processing, pp 6128\u20136137","DOI":"10.18653\/v1\/2021.emnlp-main.495"},{"key":"1698_CR13","unstructured":"Gundapu S, Mamidi R (2018) Word level language identification in English Telugu code mixed data. In: Proceedings of the 32nd Pacific Asia conference on language, information and computation"},{"key":"1698_CR14","doi-asserted-by":"crossref","unstructured":"Hande A, Hegde SU, Priyadharshini R, et\u00a0al (2021a) Benchmarking multi-task learning for sentiment analysis and offensive language identification in under-resourced Dravidian languages. arXiv preprint arXiv:2108.03867","DOI":"10.1007\/s42488-022-00070-w"},{"key":"1698_CR15","unstructured":"Hande A, Puranik K, Yasaswini K, et\u00a0al (2021b) Offensive language identification in low-resourced code-mixed Dravidian languages using pseudo-labeling. arXiv preprint arXiv:2108.12177"},{"key":"1698_CR16","unstructured":"Houlsby N, Giurgiu A, Jastrzebski S, et\u00a0al (2019) Parameter-efficient transfer learning for nlp. In: International conference on machine learning. PMLR, pp 2790\u20132799"},{"key":"1698_CR17","doi-asserted-by":"crossref","unstructured":"Huertas\u00a0Garc\u00eda \u00c1, et\u00a0al (2021) Automatic information search for countering Covid-19 misinformation through semantic similarity. Master\u2019s thesis","DOI":"10.1007\/978-3-030-91608-4_31"},{"key":"1698_CR18","first-page":"4948","volume":"2020","author":"D Kakwani","year":"2020","unstructured":"Kakwani D, Kunchukuttan A, Golla S et al (2020) Indicnlpsuite: monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for Indian languages. Find Assoc Comput Linguist EMNLP 2020:4948\u20134961","journal-title":"Find Assoc Comput Linguist EMNLP"},{"key":"1698_CR19","unstructured":"Kamble S, Joshi A (2018) Hate speech detection from code-mixed Hindi-English tweets using deep learning models. arXiv preprint arXiv:1811.05145"},{"key":"1698_CR20","doi-asserted-by":"crossref","unstructured":"Kazhuparambil S, Kaushik A (2020) Cooking is all about people: comment classification on cookery channels using Bert and classification models (Malayalam-English mix-code). arXiv preprint arXiv:2007.04249","DOI":"10.20944\/preprints202006.0223.v1"},{"key":"1698_CR21","unstructured":"Kenton JDMWC, Toutanova LK (2019) Bert: pre-training of deep bidirectional transformers for language understanding. Universal Language Model Fine-tuning for Text Classification p 278"},{"key":"1698_CR22","unstructured":"Khandelwal A, Swami S, Akthar SS, et\u00a0al (2019) Humor detection in English-Hindi code-mixed social media content: Corpus and baseline system. In: 11th international conference on language resources and evaluation, LREC 2018, European language resources association (ELRA), pp 1203\u20131207"},{"key":"1698_CR23","doi-asserted-by":"crossref","unstructured":"Khanuja S, Dandapat S, Srinivasan A, et\u00a0al (2020) Gluecos: an evaluation benchmark for code-switched nlp. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 3575\u20133585","DOI":"10.18653\/v1\/2020.acl-main.329"},{"key":"1698_CR24","unstructured":"Libovick\u1ef3 J, Rosa R, Fraser A (2019) How language-neutral is multilingual Bert? arXiv preprint arXiv:1911.03310"},{"key":"1698_CR25","doi-asserted-by":"crossref","unstructured":"Mathur P, Sawhney R, Ayyar M, et\u00a0al (2018a) Did you offend me? Classification of offensive tweets in Hinglish language. In: Proceedings of the 2nd workshop on abusive language online (ALW2), pp 138\u2013148","DOI":"10.18653\/v1\/W18-5118"},{"key":"1698_CR26","first-page":"18","volume":"2018","author":"P Mathur","year":"2018","unstructured":"Mathur P, Shah RR, Sawhney R et al (2018) Detecting offensive tweets in Hindi-English code-switched language. ACL 2018:18","journal-title":"ACL"},{"key":"1698_CR27","first-page":"51","volume":"2018","author":"D Mave","year":"2018","unstructured":"Mave D, Maharjan S, Solorio T (2018) Language identification and analysis of code-switched social media text. ACL 2018:51","journal-title":"ACL"},{"key":"1698_CR28","first-page":"40","volume":"2016","author":"G Molina","year":"2016","unstructured":"Molina G, Rey-Villamizar N, Solorio T et al (2016) Overview for the second shared task on language identification in code-switched data. EMNLP 2016:40","journal-title":"EMNLP"},{"key":"1698_CR29","doi-asserted-by":"crossref","unstructured":"Ousidhoum N, Lin Z, Zhang H, et\u00a0al (2019) Multilingual and multi-aspect hate speech analysis. In: EMNLP\/IJCNLP (1)","DOI":"10.18653\/v1\/D19-1474"},{"key":"1698_CR30","doi-asserted-by":"crossref","unstructured":"Pfeiffer J, R\u00fcckl\u00e9 A, Poth C, et\u00a0al (2020a) Adapterhub: a framework for adapting transformers. In: Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations, pp 46\u201354","DOI":"10.18653\/v1\/2020.emnlp-demos.7"},{"key":"1698_CR31","doi-asserted-by":"crossref","unstructured":"Pfeiffer J, Vuli\u0107 I, Gurevych I, et\u00a0al (2020b) Mad-x: An adapter-based framework for multi-task cross-lingual transfer. In: Proceedings of the 2020 Conference on empirical methods in natural language processing (EMNLP), pp 7654\u20137673","DOI":"10.18653\/v1\/2020.emnlp-main.617"},{"key":"1698_CR32","doi-asserted-by":"crossref","unstructured":"Pfeiffer J, Kamath A, R\u00fcckl\u00e9 A, et\u00a0al (2021) Adapterfusion: non-destructive task composition for transfer learning. In: Proceedings of the 16th conference of the european chapter of the association for computational linguistics: main volume, pp 487\u2013503","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"1698_CR33","unstructured":"R\u00fcckl\u00e9 A (2021) Representation learning and learning from limited labeled data for community question answering"},{"key":"1698_CR34","doi-asserted-by":"crossref","unstructured":"R\u00fcckl\u00e9 A, Geigle G, Glockner M, et\u00a0al (2021) Adapterdrop: on the efficiency of adapters in transformers. In: Proceedings of the 2021 conference on empirical methods in natural language processing, pp 7930\u20137946","DOI":"10.18653\/v1\/2021.emnlp-main.626"},{"key":"1698_CR35","doi-asserted-by":"crossref","unstructured":"Sabty C, Elmahdy M, Abdennadher S (2019) Named entity recognition on Arabic-English code-mixed data. In: 2019 IEEE 13th international conference on semantic computing (ICSC), IEEE computer society, pp 93\u201397","DOI":"10.1109\/ICOSC.2019.8665500"},{"key":"1698_CR36","unstructured":"Senevirathne L, Demotte P, Karunanayake B, et\u00a0al (2020) Sentiment analysis for Sinhala language using deep learning techniques. arXiv preprint arXiv:2011.07280"},{"key":"1698_CR37","doi-asserted-by":"crossref","unstructured":"Smith I, Thayasivam U (2019) Language detection in Sinhala-English code-mixed data. In: 2019 International conference on Asian language processing (IALP). IEEE, pp 228\u2013233","DOI":"10.1109\/IALP48816.2019.9037680"},{"key":"1698_CR38","first-page":"62","volume":"2014","author":"T Solorio","year":"2014","unstructured":"Solorio T, Blair E, Maharjan S et al (2014) Overview for the first shared task on language identification in code-switched data. EMNLP 2014:62","journal-title":"EMNLP"},{"key":"1698_CR39","unstructured":"Swami S, Khandelwal A, Singh V, et\u00a0al (2018) A corpus of English-Hindi code-mixed tweets for sarcasm detection. Scanning Electron Microsc Meet at"},{"key":"1698_CR40","doi-asserted-by":"crossref","unstructured":"Toftrup M, S\u00f8rensen SA, Ciosici MR, et\u00a0al (2021) A reproduction of apple\u2019s bi-directional lstm models for language identification in short strings. In: Proceedings of the 16th conference of the european chapter of the association for computational linguistics: student research workshop, pp 36\u201342","DOI":"10.18653\/v1\/2021.eacl-srw.6"},{"key":"1698_CR41","doi-asserted-by":"crossref","unstructured":"\u00dcnal U, Da\u011f H (2022) Anomalyadapters: parameter-efficient multi-anomaly task detection. IEEE Access","DOI":"10.1109\/ACCESS.2022.3141161"},{"key":"1698_CR42","unstructured":"Vaswani A, Shazeer N, Parmar N, et\u00a0al (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"1698_CR43","unstructured":"Vilares D, Alonso MA, G\u00f3mez-Rodr\u00edguez C (2016) En-es-cs: an English-Spanish code-switching twitter corpus for multilingual sentiment analysis. In: Proceedings of the tenth international conference on language resources and evaluation (LREC\u201916), pp 4149\u20134153"},{"key":"1698_CR44","doi-asserted-by":"publisher","first-page":"730","DOI":"10.18653\/v1\/2021.findings-emnlp.63","volume":"2021","author":"X Wang","year":"2021","unstructured":"Wang X, Tsvetkov Y, Ruder S et al (2021) Efficient test time adapter ensembling for low-resource language varieties. Find Assoc Comput Linguist EMNLP 2021:730\u2013737","journal-title":"Find Assoc Comput Linguist EMNLP"},{"key":"1698_CR45","unstructured":"Yadav S, Chakraborty T (2020) Unsupervised sentiment analysis for code-mixed data. arXiv preprint arXiv:2001.11384"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-022-01698-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-022-01698-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-022-01698-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T04:19:51Z","timestamp":1657858791000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-022-01698-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":45,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["1698"],"URL":"https:\/\/doi.org\/10.1007\/s10115-022-01698-1","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]},"assertion":[{"value":"22 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The four authors of this paper have no conflict of interest to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Ethical approval is not applicable. Data annotators were informed about the task prior to the work and were paid according to the institution approved rates.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"We would like to confirm that this work is original and has not been published elsewhere, nor is it currently under consideration for publication elsewhere. All the authors give their consent to publish the manuscript.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}