{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:52:44Z","timestamp":1773658364033,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s13042-025-02950-0","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T14:43:01Z","timestamp":1769697781000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Assamese information retrieval using classification and embedding techniques"],"prefix":"10.1007","volume":"17","author":[{"given":"Manash Pratim","family":"Lahkar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Utpal","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tribikram","family":"Pradhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"2950_CR1","unstructured":"Almeida A, Bhattacharyya P (2008) Using morphology to improve marathi monolingual information retrieval. Indian Institute of Technology, Bombay India Source http:\/\/www isical ac in\/$$^{\\sim }$$ fire\/paper\/Ashish_almeida-IITB-fire2008 pdf"},{"issue":"4","key":"2950_CR2","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1145\/582415.582416","volume":"20","author":"G Amati","year":"2002","unstructured":"Amati G, Van Rijsbergen CJ (2002) Probabilistic models of information retrieval based on measuring the divergence from randomness. ACM Trans Inf Syst 20(4):357\u2013389","journal-title":"ACM Trans Inf Syst"},{"issue":"2","key":"2950_CR3","first-page":"1","volume":"8","author":"AK Barman","year":"2019","unstructured":"Barman AK, Sarmah J, Sarma SK (2019) Developing assamese information retrieval system considering nlp techniques: an attempt for a low resourced language. ADBU J Eng Technol 8(2):1\u201312","journal-title":"ADBU J Eng Technol"},{"key":"2950_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121629","volume":"238","author":"AP Bhopale","year":"2024","unstructured":"Bhopale AP, Tiwari A (2024) Transformer based contextual text representation framework for intelligent information retrieval. Expert Syst Appl 238:121629","journal-title":"Expert Syst Appl"},{"key":"2950_CR5","volume-title":"Introduction to modern information retrieval","author":"GG Chowdhury","year":"2010","unstructured":"Chowdhury GG (2010) Introduction to modern information retrieval. Facet publishing"},{"issue":"1","key":"2950_CR6","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1017\/S1351324916000334","volume":"23","author":"KW Church","year":"2017","unstructured":"Church KW (2017) Word2vec. Nat Lang Eng 23(1):155\u2013162","journal-title":"Nat Lang Eng"},{"key":"2950_CR7","doi-asserted-by":"crossref","unstructured":"Conneau A, Khandelwal K, Goyal N, et\u00a0al (2019) Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"2950_CR8","doi-asserted-by":"crossref","unstructured":"Doddapaneni S, Aralikatte R, Ramesh G et al (2023). In: Rogers A, Boyd-Graber J, Okazaki N (eds) Towards leaving no Indic language behind: Building monolingual corpora, benchmark and models for Indic languages. Association for Computational Linguistics, Toronto, Canada","DOI":"10.18653\/v1\/2023.acl-long.693"},{"key":"2950_CR9","first-page":"189","volume":"38","author":"ST Dumais","year":"2004","unstructured":"Dumais ST (2004) Latent semantic analysis. Annu Rev Inf Sci Technol (ARIST) 38:189\u2013230","journal-title":"Annu Rev Inf Sci Technol (ARIST)"},{"issue":"6","key":"2950_CR10","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.3390\/electronics14061210","volume":"14","author":"N Fragakis","year":"2025","unstructured":"Fragakis N, Trichopoulos G, Caridakis G (2025) Empowering education with intelligent systems: exploring large language models and the Nao robot for information retrieval. Electronics 14(6):1210","journal-title":"Electronics"},{"issue":"5","key":"2950_CR11","first-page":"1763","volume":"13","author":"A Gogoi","year":"2021","unstructured":"Gogoi A, Baruah N, Sarma SK et al (2021) Improving stemming for assamese information retrieval. Int J Inf Technol 13(5):1763\u20131768","journal-title":"Int J Inf Technol"},{"key":"2950_CR12","doi-asserted-by":"crossref","unstructured":"Gong Y, Cosma G (2023) Boon: a neural search engine for cross-modal information retrieval. arXiv preprint arXiv:2307.14240","DOI":"10.1145\/3606040.3617440"},{"key":"2950_CR13","doi-asserted-by":"crossref","unstructured":"Hiemstra D (2009) Information retrieval models. Information retrieval: searching in the 21st Century. pp 1\u201319","DOI":"10.1002\/9780470033647.ch1"},{"issue":"6","key":"2950_CR14","doi-asserted-by":"publisher","first-page":"2181","DOI":"10.1109\/TVCG.2019.2903946","volume":"25","author":"X Ji","year":"2019","unstructured":"Ji X, Shen HW, Ritter A et al (2019) Visual exploration of neural document embedding in information retrieval: semantics and feature selection. IEEE Trans Vis Comput Graph 25(6):2181\u20132192","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"2950_CR15","unstructured":"Joshi ML, Mittal N, Joshi N (2017) An insight into role of wordnet and language network for effective ir from hindi text documents. pp 158\u2013163"},{"key":"2950_CR16","doi-asserted-by":"crossref","unstructured":"Kakwani D, Kunchukuttan A, Golla S, et\u00a0al (2020) IndicNLPSuite: monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for indian languages. In: Findings of EMNLP","DOI":"10.18653\/v1\/2020.findings-emnlp.445"},{"key":"2950_CR17","unstructured":"Khanuja S, Bansal D, Mehtani S, et\u00a0al (2020) Muril: multilingual representations for Indian languages. arxiv 2021. arXiv preprint arXiv:2103.10730"},{"key":"2950_CR18","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3491593","author":"M Kowsher","year":"2019","unstructured":"Kowsher M, Hossen I, Ahmed S (2019) Bengali information retrieval system (birs). Int J Natl Language Comput (IJNLC). https:\/\/doi.org\/10.2139\/ssrn.3491593","journal-title":"Int J Natl Language Comput (IJNLC)"},{"key":"2950_CR19","unstructured":"Lan Z, Chen M, Goodman S, et\u00a0al (2019) Albert: a lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942"},{"issue":"2","key":"2950_CR20","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/52.582976","volume":"14","author":"DL Lee","year":"1997","unstructured":"Lee DL, Chuang H, Seamons K (1997) Document ranking and the vector-space model. IEEE Softw 14(2):67\u201375","journal-title":"IEEE Softw"},{"issue":"3","key":"2950_CR21","first-page":"1","volume":"43","author":"X Li","year":"2025","unstructured":"Li X, Jin J, Zhou Y et al (2025) From matching to generation: a survey on generative information retrieval. ACM Trans Inf Syst 43(3):1\u201362","journal-title":"ACM Trans Inf Syst"},{"key":"2950_CR22","unstructured":"Macdonald C, Ounis I (2006) The trec blogs06 collection: Creating and analysing a blog test collection. Department of Computer Science, University of Glasgow Tech Report TR-2006-224 1:3\u20131"},{"key":"2950_CR23","unstructured":"Macdonald C, McCreadie R, Santos RL, et\u00a0al (2012) From puppy to maturity: experiences in developing terrier. Proc of OSIR at SIGIR pp 60\u201363"},{"key":"2950_CR24","unstructured":"Mikolov T, Grave E, Bojanowski P, et\u00a0al (2018) Advances in pre-training distributed word representations. In: Proceedings of the international conference on language resources and evaluation (LREC 2018)"},{"key":"2950_CR25","doi-asserted-by":"crossref","unstructured":"Mishra A, Vishwakarma S (2015) Analysis of tf-idf model and its variant for document retrieval. pp 772\u2013776","DOI":"10.1109\/CICN.2015.157"},{"issue":"3","key":"2950_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-025-03707-w","volume":"6","author":"HT Nguyen","year":"2025","unstructured":"Nguyen HT, Duong KH, Pham LTT et al (2025) Inverted index for similar document detection: a case study at Can Tho University journal of science. SN Comput Sci 6(3):216","journal-title":"SN Comput Sci"},{"key":"2950_CR27","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"2950_CR28","doi-asserted-by":"crossref","unstructured":"RAHMAN N, Choudhury P, Guha P, et\u00a0al (2025) Visual question answering in low-resource assamese language-datasets and evaluation. Available at SSRN 5078748","DOI":"10.2139\/ssrn.5078748"},{"issue":"5","key":"2950_CR29","doi-asserted-by":"publisher","first-page":"856","DOI":"10.4218\/etrij.2019-0458","volume":"43","author":"I Rasheed","year":"2021","unstructured":"Rasheed I, Banka H, Khan HM (2021) Building a text collection for Urdu information retrieval. ETRI J 43(5):856\u2013868","journal-title":"ETRI J"},{"issue":"4","key":"2950_CR30","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1561\/1500000019","volume":"3","author":"S Robertson","year":"2009","unstructured":"Robertson S, Zaragoza H (2009) The probabilistic relevance framework: BM25 and beyond. Found Trends\u00ae Inf Retr 3(4):333\u2013389","journal-title":"Found Trends\u00ae Inf Retr"},{"key":"2950_CR31","volume-title":"Information retrieval models: foundations & relationships","author":"T Roelleke","year":"2022","unstructured":"Roelleke T (2022) Information retrieval models: foundations & relationships. Springer Nature"},{"issue":"1","key":"2950_CR32","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/s12046-021-01731-z","volume":"47","author":"SS Sahu","year":"2022","unstructured":"Sahu SS, Pal S (2022) Effect of stopwords in indian language ir. S\u0101dhan\u0101 47(1):17","journal-title":"S\u0101dhan\u0101"},{"issue":"11","key":"2950_CR33","doi-asserted-by":"publisher","first-page":"1022","DOI":"10.1145\/182.358466","volume":"26","author":"G Salton","year":"1983","unstructured":"Salton G, Fox EA, Wu H (1983) Extended boolean information retrieval. Commun ACM 26(11):1022\u20131036","journal-title":"Commun ACM"},{"key":"2950_CR34","unstructured":"Sarma PSK (2019) Assamese stopwords. CLARIN-PL digital repository"},{"key":"2950_CR35","doi-asserted-by":"crossref","unstructured":"Sharma S (2021) Morphophonemic variation in the nominal morphology of assamese. Himalayan Linguistics 20(2)","DOI":"10.5070\/H920254239"},{"key":"2950_CR36","doi-asserted-by":"crossref","unstructured":"Soboroff I (2021) Overview of trec, (2021) In: 30th text retrieval conference. Gaithersburg, Maryland","DOI":"10.6028\/NIST.SP.500-335.overview-overview"},{"key":"2950_CR37","unstructured":"Tala F (2003) A study of stemming effects on information retrieval in bahasa indonesia. Institute for Logic, Language and Computation Universiteit van Amsterdam The Netherlands"},{"key":"2950_CR38","unstructured":"Wang S, Koopman R (2017) Semantic embedding for information retrieval. In: BIR@ ECIR, pp 122\u2013132"},{"key":"2950_CR39","doi-asserted-by":"crossref","unstructured":"Wu L, Yen IE, Xu K et al (2018) Word mover\u2019s embedding: From word2vec to document embedding arXiv preprint arXiv:1811.01713","DOI":"10.18653\/v1\/D18-1482"},{"key":"2950_CR40","doi-asserted-by":"publisher","unstructured":"Xu C, Si J, Guan Z et al (2024) Reliable conflictive multi-view learning. In: Proceedings of the AAAI conference on artificial intelligence 38(14):16129\u201316137. https:\/\/doi.org\/10.1609\/aaai.v38i14.29546 (https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/29546)","DOI":"10.1609\/aaai.v38i14.29546"},{"key":"2950_CR41","doi-asserted-by":"publisher","unstructured":"Xu C, Zhang Y, Guan Z, et\u00a0al (2024b) Trusted multi-view learning with label noise. In: Larson K (ed) Proceedings of the thirty-third international joint conference on artificial intelligence, IJCAI-24. International joint conferences on artificial intelligence organization, pp 5263\u20135271, https:\/\/doi.org\/10.24963\/ijcai.2024\/582, main Track","DOI":"10.24963\/ijcai.2024\/582"},{"key":"2950_CR42","doi-asserted-by":"crossref","unstructured":"Ye X, Shen H, Ma X et al (2016) From word embeddings to document similarities for improved information retrieval in software engineering. pp 404\u2013415","DOI":"10.1145\/2884781.2884862"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02950-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02950-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02950-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T09:54:42Z","timestamp":1773654882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02950-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,29]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2950"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02950-0","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,29]]},"assertion":[{"value":"6 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2026","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 authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"51"}}