{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T12:52:15Z","timestamp":1781527935997,"version":"3.54.1"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012624","name":"Tezpur University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012624","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.ins.2026.123645","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:13:48Z","timestamp":1779380028000},"page":"123645","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Generative pre-training for low-resource question answering: Integrating morphological constraints in assamese language modeling"],"prefix":"10.1016","volume":"754","author":[{"given":"Manash Pratim","family":"Lahkar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tribikram","family":"Pradhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Utpal","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2026.123645_bib0005","series-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","first-page":"2227","article-title":"Deep contextualized word representations","author":"Peters","year":"2018"},{"key":"10.1016\/j.ins.2026.123645_bib0010","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123645_bib0015","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.ins.2026.123645_bib0020","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"10.1016\/j.ins.2026.123645_bib0025","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","first-page":"784","article-title":"Know what you don\u2019t know: unanswerable questions for squad","author":"Rajpurkar","year":"2018"},{"key":"10.1016\/j.ins.2026.123645_bib0030","series-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)","doi-asserted-by":"crossref","DOI":"10.63317\/2gscircifffd","article-title":"SentEval: an evaluation toolkit for universal sentence representations","author":"Conneau","year":"2018"},{"key":"10.1016\/j.ins.2026.123645_bib0035","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123645_bib0040","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"6282","article-title":"The state and Fate of linguistic diversity and inclusion in the NLP world","author":"Joshi","year":"2020"},{"key":"10.1016\/j.ins.2026.123645_bib0045","article-title":"Odner: NER resource creation and system development for low-resource odia language","volume":"11","author":"Dalai","year":"2025","journal-title":"J. Nat. Lang. Process."},{"key":"10.1016\/j.ins.2026.123645_bib0050","series-title":"Proceedings of the Tenth Conference on Machine Translation","first-page":"1222","article-title":"Delab-IIITM WMT25: enhancing low-resource machine translation for manipuri and assamese","author":"Oinam","year":"2025"},{"key":"10.1016\/j.ins.2026.123645_bib0055","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1017\/nlp.2024.15","article-title":"Part-of-speech tagger for bodo language using deep learning approach","volume":"31","author":"Pathak","year":"2025","journal-title":"Nat. Lang. Process."},{"key":"10.1016\/j.ins.2026.123645_bib0060","series-title":"Structure of Assamese","author":"Goswami","year":"1982"},{"key":"10.1016\/j.ins.2026.123645_bib0065","series-title":"Findings of the Association for Computational Linguistics: ACL 2023","article-title":"Axomiyaberta: a phonologically-aware transformer model for assamese","author":"Nath","year":"2023"},{"key":"10.1016\/j.ins.2026.123645_bib0070","series-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"1715","article-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2016"},{"key":"10.1016\/j.ins.2026.123645_bib0075","author":"Wu"},{"key":"10.1016\/j.ins.2026.123645_bib0080","series-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","first-page":"66","article-title":"Sentencepiece: a simple and language independent subword tokenizer and detokenizer for neural text processing","author":"Kudo","year":"2018"},{"key":"10.1016\/j.ins.2026.123645_bib0085","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1187415.1187418","article-title":"Unsupervised models for morpheme segmentation and morphology learning","volume":"4","author":"Creutz","year":"2007","journal-title":"ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.ins.2026.123645_bib0090","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1515\/pralin-2017-0031","article-title":"Linguistically motivated vocabulary reduction for neural machine translation from turkish to english","volume":"108","author":"Ataman","year":"2017","journal-title":"Prague Bull. Math. Linguist."},{"key":"10.1016\/j.ins.2026.123645_bib0095","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"1882","article-title":"Bpe-dropout: simple and effective subword regularization","author":"Provilkov","year":"2020"},{"key":"10.1016\/j.ins.2026.123645_bib0100","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1162\/tacl_a_00461","article-title":"Byt5: towards a token-free future with pre-trained byte-to-byte models","volume":"10","author":"Xue","year":"2022","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.ins.2026.123645_bib0105","series-title":"Papers in Structural and Transformational Linguistics","first-page":"32","article-title":"From phoneme to morpheme","author":"Harris","year":"1970"},{"key":"10.1016\/j.ins.2026.123645_bib0110","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"66","article-title":"Subword regularization: improving neural network translation models with multiple subword candidates","author":"Kudo","year":"2018"},{"key":"10.1016\/j.ins.2026.123645_bib0115","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1162\/tacl_a_00448","article-title":"Canine: pre-training an efficient tokenization-free encoder for language representation","volume":"10","author":"Clark","year":"2022","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.ins.2026.123645_bib0120","series-title":"Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers","first-page":"1177","article-title":"Morfessor flatcat: an HMM-based method for unsupervised and semi-supervised learning of morphology","author":"Gr\u00f6nroos","year":"2014"},{"key":"10.1016\/j.ins.2026.123645_bib0125","series-title":"Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)","first-page":"97","article-title":"An evaluation of two vocabulary reduction methods for neural machine translation","author":"Ataman","year":"2018"},{"key":"10.1016\/j.ins.2026.123645_bib0130","series-title":"International Conference on Machine Learning","first-page":"1899","article-title":"Compositional morphology for word representations and language modelling","author":"Botha","year":"2014"},{"key":"10.1016\/j.ins.2026.123645_bib0135","series-title":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"1287","article-title":"Morphological word-embeddings","author":"Cotterell","year":"2015"},{"key":"10.1016\/j.ins.2026.123645_bib0140","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"4729","article-title":"Zen: pre-training Chinese text encoder enhanced by n-gram representations","author":"Diao","year":"2020"},{"key":"10.1016\/j.ins.2026.123645_bib0145","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Character-aware neural language models","volume":"vol. 30","author":"Kim","year":"2016"},{"key":"10.1016\/j.ins.2026.123645_bib0150","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"4617","article-title":"Byte pair encoding is suboptimal for language model pretraining","author":"Bostrom","year":"2020"},{"key":"10.1016\/j.ins.2026.123645_bib0155","series-title":"Proceedings of the 26th Annual International Conference on Machine Learning","first-page":"41","article-title":"Curriculum learning","author":"Bengio","year":"2009"},{"key":"10.1016\/j.ins.2026.123645_bib0160","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"1162","article-title":"Competence-based curriculum learning for neural machine translation","author":"Platanios","year":"2019"},{"key":"10.1016\/j.ins.2026.123645_bib0165","first-page":"4555","article-title":"A survey on curriculum learning","volume":"44","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.ins.2026.123645_bib0170","series-title":"2022 IEEE\/ACS 19th International Conference on Computer Systems and Applications (AICCSA)","first-page":"1","article-title":"Aspos: assamese part of speech tagger using deep learning approach","author":"Pathak","year":"2022"},{"key":"10.1016\/j.ins.2026.123645_bib0175","first-page":"1","article-title":"Named entity recognition in assamese","volume":"142","author":"Sharma","year":"2016","journal-title":"Int. J. Comput. Appl."},{"key":"10.1016\/j.ins.2026.123645_bib0180","doi-asserted-by":"crossref","first-page":"1707","DOI":"10.1016\/j.procs.2024.04.161","article-title":"Deep learning based part-of-speech tagging for assamese using RNN and GRU","volume":"235","author":"Talukdar","year":"2024","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.ins.2026.123645_bib0185","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"4948","article-title":"Indicnlpsuite: monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for Indian languages","author":"Kakwani","year":"2020"},{"key":"10.1016\/j.ins.2026.123645_bib0190","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1162\/tacl_a_00452","article-title":"Samanantar: the largest publicly available parallel corpora collection for 11 indic languages","volume":"10","author":"Ramesh","year":"2022","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.ins.2026.123645_bib0195","author":"Khanuja"},{"key":"10.1016\/j.ins.2026.123645_bib0200","series-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"483","article-title":"MT5: a massively multilingual pre-trained text-to-text transformer","author":"Xue","year":"2021"},{"key":"10.1016\/j.ins.2026.123645_bib0205","author":"Tang"},{"key":"10.1016\/j.ins.2026.123645_bib0210","author":"Workshop"},{"key":"10.1016\/j.ins.2026.123645_bib0215","author":"Gemma"},{"key":"10.1016\/j.ins.2026.123645_bib0220","author":"Allal"},{"key":"10.1016\/j.ins.2026.123645_bib0225","author":"Singh"},{"key":"10.1016\/j.ins.2026.123645_bib0230","author":"Lan"},{"key":"10.1016\/j.ins.2026.123645_bib0235","author":"Hurst"},{"key":"10.1016\/j.ins.2026.123645_bib0240","author":"Jiang"},{"key":"10.1016\/j.ins.2026.123645_bib0245","author":"Wei"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526005761?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526005761?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T11:56:47Z","timestamp":1781524607000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025526005761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":49,"alternative-id":["S0020025526005761"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123645","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Generative pre-training for low-resource question answering: Integrating morphological constraints in assamese language modeling","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123645","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"123645"}}