{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T11:53:13Z","timestamp":1768477993386,"version":"3.49.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031781711","type":"print"},{"value":"9783031781728","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78172-8_17","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T09:48:34Z","timestamp":1733132914000},"page":"255-270","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["HindiLLM: Large Language Model for\u00a0Hindi"],"prefix":"10.1007","author":[{"given":"Sanjay","family":"Chouhan","sequence":"first","affiliation":[]},{"given":"Shubha Brata","family":"Nath","sequence":"additional","affiliation":[]},{"given":"Aparajita","family":"Dutta","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"17_CR1","unstructured":"Abadji, J., Suarez, P.O., Romary, L., Sagot, B.: Towards a cleaner document-oriented multilingual crawled corpus. arXiv preprint arXiv:2201.06642 (2022)"},{"key":"17_CR2","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"17_CR3","unstructured":"Anil, R., et\u00a0al.: Palm 2 technical report. arXiv preprint arXiv:2305.10403 (2023)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Arora, G.: inltk: Natural language toolkit for indic languages. arXiv preprint arXiv:2009.12534 (2020)","DOI":"10.18653\/v1\/2020.nlposs-1.10"},{"key":"17_CR5","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116 (2019)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-xl: attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860 (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"El-Kishky, A., Chaudhary, V., Guzm\u00e1n, F., Koehn, P.: Ccaligned: a massive collection of cross-lingual web-document pairs. arXiv preprint arXiv:1911.06154 (2019)","DOI":"10.18653\/v1\/2020.emnlp-main.480"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146 (2018)","DOI":"10.18653\/v1\/P18-1031"},{"key":"17_CR10","unstructured":"Hu, E.J., et al.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"17_CR11","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Kakwani, D., et al.: Indicnlpsuite: monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for Indian languages. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 4948\u20134961 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.445"},{"key":"17_CR13","unstructured":"Kunchukuttan, A., et\u00a0al.: Ai4bharat-indicnlp corpus: monolingual corpora and word embeddings for indic languages. arXiv preprint arXiv:2005.00085 (2020)"},{"key":"17_CR14","unstructured":"Kunchukuttan, A., Mehta, P., Bhattacharyya, P.: The IIT Bombay English-Hindi parallel corpus. arXiv preprint arXiv:1710.02855 (2017)"},{"key":"17_CR15","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)"},{"key":"17_CR16","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"17_CR17","unstructured":"Micikevicius, P., et\u00a0al.: Mixed precision training. arXiv preprint arXiv:1710.03740 (2017)"},{"key":"17_CR18","unstructured":"Niyogi, M., Bhattacharya, A.: Paramanu: a family of novel efficient indic generative foundation language models. arXiv preprint arXiv:2401.18034 (2024)"},{"key":"17_CR19","unstructured":"Owen, L., Tripathi, V., Kumar, A., Ahmed, B.: Komodo: a linguistic expedition into Indonesia\u2019s regional languages. arXiv preprint arXiv:2403.09362 (2024)"},{"key":"17_CR20","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9 Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 8024\u20138035. Curran Associates, Inc. (2019). http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Pires, T., Schlinger, E., Garrette, D.: How multilingual is multilingual bert? arXiv preprint arXiv:1906.01502 (2019)","DOI":"10.18653\/v1\/P19-1493"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Qi, P., Zhang, Y., Zhang, Y., Bolton, J., Manning, C.D.: Stanza: a python natural language processing toolkit for many human languages. arXiv preprint arXiv:2003.07082 (2020)","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"17_CR23","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training (2018)"},{"issue":"8","key":"17_CR24","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: Deepspeed: system optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3505\u20133506 (2020)","DOI":"10.1145\/3394486.3406703"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Ruder, S., S\u00f8gaard, A., Vuli\u0107, I.: Unsupervised cross-lingual representation learning. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts, pp. 31\u201338 (2019)","DOI":"10.18653\/v1\/P19-4007"},{"key":"17_CR27","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Uppal, S., et al.: Two-step classification using recasted data for low resource settings. In: Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pp. 706\u2013719 (2020)","DOI":"10.18653\/v1\/2020.aacl-main.71"},{"key":"17_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"de\u00a0Vries, W., Nissim, M.: As good as new. how to successfully recycle English GPT-2 to make models for other languages. arXiv preprint arXiv:2012.05628 (2020)","DOI":"10.18653\/v1\/2021.findings-acl.74"},{"key":"17_CR31","unstructured":"Wenzek, G., et al.: Ccnet: extracting high quality monolingual datasets from web crawl data. arXiv preprint arXiv:1911.00359 (2019)"},{"key":"17_CR32","unstructured":"Wolf, T., et\u00a0al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345 (2020)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78172-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T10:06:29Z","timestamp":1733133989000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78172-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031781711","9783031781728"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78172-8_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}