{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T06:12:25Z","timestamp":1765260745711,"version":"3.46.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T00:00:00Z","timestamp":1757116800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T00:00:00Z","timestamp":1757116800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Ministry of Electronics and Information Technology, Government of India","award":["11(1)\/2022-HCC(TDIL)-Part(2)","11(1)\/2022-HCC(TDIL)-Part(2)","11(1)\/2022-HCC(TDIL)-Part(2)"],"award-info":[{"award-number":["11(1)\/2022-HCC(TDIL)-Part(2)","11(1)\/2022-HCC(TDIL)-Part(2)","11(1)\/2022-HCC(TDIL)-Part(2)"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s10579-025-09859-8","type":"journal-article","created":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T08:22:03Z","timestamp":1757146923000},"page":"3851-3872","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["IL-ILGOV-2024: a translation benchmark for Hindi-to-12 languages in the governance domain"],"prefix":"10.1007","volume":"59","author":[{"given":"Vandan","family":"Mujadia","sequence":"first","affiliation":[]},{"given":"Rao B.","family":"Ashwath","sequence":"additional","affiliation":[]},{"given":"Dipti Misra","family":"Sharma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,6]]},"reference":[{"key":"9859_CR1","unstructured":"Akhbardeh, F., Arkhangorodsky, A., Biesialska, M., Bojar, O., Chatterjee, R., Chaudhary, V., Costa-jussa, M. R., Espa\u00f1a-Bonet, C., Fan, A., Federmann, C., Freitag, M., Graham, Y., Grundkiewicz, R., Haddow, B., Harter, L., Heafield, K., Homan, C., Huck, M., Amponsah-Kaakyire, K., Kasai, J., Khashabi, D., Knight, K., Kocmi, T., Koehn, P., Lourie, N., Monz, C., Morishita, M., Nagata, M., Nagesh, A., Nakazawa, T., Negri, M., Pal, S., Tapo, A. A., Turchi, M., Vydrin, V., & Zampieri, M. (2021). Findings of the 2021 conference on machine translation (WMT21). In Loic Barrault, Ondrej Bojar, Fethi Bougares, Rajen Chatterjee, Marta\u00a0R. Costa-jussa, Christian Federmann, Mark Fishel, Alexander Fraser, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Paco Guzman, Barry Haddow, Matthias Huck, Antonio\u00a0Jimeno Yepes, Philipp Koehn, Tom Kocmi, Andre Martins, Makoto Morishita, and Christof Monz, editors, Proceedings of the Sixth Conference on Machine Translation, pp. 1\u201388, Online, November. Association for Computational Linguistics."},{"key":"9859_CR2","doi-asserted-by":"crossref","unstructured":"Anastasopoulos, A., Cattelan, A., Dou, Z.-Y., Federico, M., Federman, C., Genzel, D., Guzm\u00e1n, F., Hu, J., Hughes, M., Koehn, P.,\u00a0Lazar, R.\u00a0(2020). Tico-19: The translation initiative for covid-19. arXiv preprint arXiv:2007.01788.","DOI":"10.18653\/v1\/2020.nlpcovid19-2.5"},{"key":"9859_CR3","unstructured":"Bansal, A., Banerjee, E., & Jha, G. N. (2013). Corpora creation for indian language technologies\u2014The ilci project. In the sixth Proceedings of Language Technology Conference (LTC \u201813)."},{"key":"9859_CR4","doi-asserted-by":"crossref","unstructured":"Barrault, L., Biesialska, M., Bojar, O., Costa-juss\u00e0, M. R., Federmann, C., Graham, Y., Grundkiewicz, R., Haddow, B., Huck, M., Joanis, E., Kocmi, T., Koehn, P., Lo, C.-k., Ljube\u0161i\u0107, N., Monz, C., Morishita, M., Nagata, M., Nakazawa, T., Pal, S., Post, M., & Zampieri, M. (2020). Findings of the 2020 conference on machine translation (WMT20). In L. Barrault, O. Bojar, F. Bougares, R. Chatterjee, M.\u00a0R. Costa-juss\u00e0, C. Federmann, M. Fishel, A. Fraser, Y. Graham, P. Guzman, B. Haddow, M. Huck, A.\u00a0J. Yepes, P. Koehn, A. Martins, M. Morishita, C. Monz, M. Nagata, T. Nakazawa, & M. Negri (Eds.),\u00a0Proceedings of the Fifth Conference on Machine Translation, pp. 1\u201355, Online, November. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W19-5301"},{"key":"9859_CR5","doi-asserted-by":"crossref","unstructured":"Barrault, L., Bojar, O., Costa-juss\u00e0, M. R., Federmann, C., Fishel, M., Graham, Y., Haddow, B., Huck, M., Koehn, P., Malmasi, S., Monz, C., M\u00fcller, M., Pal, S., Post, M., & Zampieri, M. (2019). Findings of the 2019 conference on machine translation (WMT19). In\u00a0O. Bojar, R. Chatterjee,\u00a0C. Federmann,\u00a0M. Fishel,\u00a0Y. Graham, B. Haddow,\u00a0M. Huck,\u00a0A. J. Yepes,\u00a0P. Koehn, A. Martins,\u00a0C. Monz, M. Negri, A. N\u00e9v\u00e9ol, M. Neves, M. Post, M. Turchi, &\u00a0K. Verspoor (Eds.), Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 1\u201361, Florence, Italy, August. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W19-5301"},{"key":"9859_CR6","doi-asserted-by":"crossref","unstructured":"Bizzoni, Y., Juzek, T. S., Espa\u00f1a-Bonet, C., Chowdhury, K. D., van Genabith, J., & Teich, E. (2020). How human is machine translationese? Comparing human and machine translations of text and speech. In Proceedings of the 17th International conference on spoken language translation, pages 280\u2013290.","DOI":"10.18653\/v1\/2020.iwslt-1.34"},{"key":"9859_CR7","doi-asserted-by":"crossref","unstructured":"Bojar, O., Buck, C., Federmann, C., Haddow, B., Koehn, P., Monz, C., Post, M., & Specia, L. (2014). Proceedings of the Ninth Workshop on Statistical Machine Translation, Baltimore, Maryland, USA, June. Association for Computational Linguistics.","DOI":"10.3115\/v1\/W14-3302"},{"key":"9859_CR8","doi-asserted-by":"crossref","unstructured":"Chimoto, E., & Bassett, B. (2022). COMET-QE and active learning for low-resource machine translation. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors, Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 4735\u20134740, Abu Dhabi, United Arab Emirates, December. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.findings-emnlp.348"},{"key":"9859_CR9","doi-asserted-by":"crossref","unstructured":"Federmann, C., Kocmi, T., & Xin, Y. (2022). Ntrex-128-news test references for mt evaluation of 128 languages. In Proceedings of the First Workshop on Scaling Up Multilingual Evaluation, 21\u201324.","DOI":"10.18653\/v1\/2022.sumeval-1.4"},{"key":"9859_CR10","unstructured":"Feng, F., Yang, Y., Cer, D., Arivazhagan, N., & Wang, W. (2020). Language-agnostic bert sentence embedding. arXiv preprint arXiv:2007.01852."},{"key":"9859_CR11","unstructured":"Gala, J., Chitale, P. A., AK, R., Doddapaneni, S., Gumma, V., Kumar, A., Nawale, J., Sujatha, A., Puduppully, R., Raghavan, V., &\u00a0Kumar, P.\u00a0(2023). Indictrans2: Towards high-quality and accessible machine translation models for all 22 scheduled indian languages. arXiv preprint arXiv:2305.16307."},{"key":"9859_CR12","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1162\/tacl_a_00474","volume":"10","author":"N Goyal","year":"2022","unstructured":"Goyal, N., Gao, C., Chaudhary, V., Chen, P.-J., Wenzek, G., Da, J., Krishnan, S., Ranzato, M. A., Guzm\u00e1n, F., & Fan, A. (2022). The flores-101 evaluation benchmark for low-resource and multilingual machine translation. Transactions of the Association for Computational Linguistics, 10, 522\u2013538.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"9859_CR13","doi-asserted-by":"crossref","unstructured":"Graham, Y., Haddow, B., & Koehn, P. (2020). Statistical power and translationese in machine translation evaluation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 72\u201381.","DOI":"10.18653\/v1\/2020.emnlp-main.6"},{"key":"9859_CR14","doi-asserted-by":"crossref","unstructured":"Guzm\u00e1n, F., Chen, P. J., Ott, M., Pino, J., Lample, G., Koehn, P., Chaudhary, V., & Ranzato, M. (2019). Two new evaluation datasets for low-resource machine translation: Nepali-English and Sinhala-English. arxiv 2019. arXiv preprint arXiv:1902.01382.","DOI":"10.18653\/v1\/D19-1632"},{"key":"9859_CR15","unstructured":"Heafield, K. (2011). Kenlm: Faster and smaller language model queries. In Proceedings of the sixth workshop on statistical machine translation, 187\u2013197."},{"key":"9859_CR16","unstructured":"Karakanta, A., Ojha, A. K., Liu, C.-H., Washington, J., Oco, N., Lakew, S. M., Malykh, V., & Zhao, X. (2019). editors. Proceedings of the 2nd Workshop on Technologies for MT of Low Resource Languages, Dublin, Ireland, August. European Association for Machine Translation."},{"key":"9859_CR17","doi-asserted-by":"crossref","unstructured":"Khan, M. S. U. R., Mehta, P., Sankar, A., Kumaravelan, U., Doddapaneni, S., Jain, S., Kunchukuttan, A., Kumar, P., Dabre, R., Khapra, M. M. (2024). Indicllmsuite: A blueprint for creating pre-training and fine-tuning datasets for indian languages. arXiv preprint arXiv:2403.06350.","DOI":"10.18653\/v1\/2024.acl-long.843"},{"key":"9859_CR18","unstructured":"Kunchukuttan, A., Mehta, P., & Bhattacharyya. P. (2018). The IIT Bombay English-Hindi parallel corpus. In Nicoletta Calzolari, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Koiti Hasida, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, H\u00e9l\u00e8ne Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis, and Takenobu Tokunaga, editors, Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan, May. European Language Resources Association (ELRA)."},{"key":"9859_CR19","unstructured":"Mikolov, T., Grave, E., Bojanowski, P., Puhrsch, C., & Joulin, A. (2018). Advances in pre-training distributed word representations. In Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018)."},{"key":"9859_CR20","unstructured":"Ministry of Education Government of India. Indian languages.\u00a0Retrieved July 29, 2024, from\u00a0https:\/\/www.education.gov.in\/sites\/upload_files\/mhrd\/files\/upload_document\/languagebr.pdf."},{"key":"9859_CR21","unstructured":"Mujadia, V., Mishra, P., Ahsan, A., & Sharma, D. M. (2023). Towards large language model driven reference-less translation evaluation for English and Indian language. In Jyoti D.\u00a0Pawar and Sobha Lalitha\u00a0Devi, editors, Proceedings of the 20th International Conference on Natural Language Processing (ICON), pages 357\u2013369, Goa University, Goa, India, December. NLP Association of India (NLPAI)."},{"key":"9859_CR22","unstructured":"Mujadia, V., & Sharma, D. (2022). The LTRC Hindi-Telugu parallel corpus. In Nicoletta Calzolari, Fr\u00e9d\u00e9ric B\u00e9chet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, H\u00e9l\u00e8ne Mazo, Jan Odijk, and Stelios Piperidis, editors, Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 3417\u20133424, Marseille, France, June. European Language Resources Association."},{"key":"9859_CR23","doi-asserted-by":"crossref","unstructured":"Ojha, A. K., Malykh, Karakanta, A., & Liu, C.-H. (2020). Findings of the loresmt 2020 shared task on zero-shot for low-resource languages. In Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages, pp. 33\u201337.","DOI":"10.18653\/v1\/2020.loresmt-1.4"},{"key":"9859_CR24","unstructured":"Ortega, J., Ojha, A. K., Kann, K., & Liu, C.-H. (2021). In Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)."},{"key":"9859_CR25","doi-asserted-by":"crossref","unstructured":"Pal, S., Pakray, P., Laskar, S. R., Laitonjam, L., Khenglawt, V., Warjri, S., Dadure, P. K., & Dash, S. K. (2023). Findings of the WMT 2023 shared task on low-resource Indic language translation. In Philipp Koehn, Barry Haddow, Tom Kocmi, and Christof Monz, editors, Proceedings of the Eighth Conference on Machine Translation, pp. 682\u2013694, Singapore, December. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.wmt-1.56"},{"key":"9859_CR26","unstructured":"Rajan, R. (2020). Quantitative analysis of the morphological complexity of malayalam language."},{"key":"9859_CR27","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1162\/tacl_a_00452","volume":"10","author":"G Ramesh","year":"2022","unstructured":"Ramesh, G., Doddapaneni, S., Bheemaraj, A., Jobanputra, M., Raghavan, A. K., Sharma, A., Sahoo, S., Diddee, H., Mahalakshmi, J., Kakwani, D., Kumar, N., Pradeep, A., Nagaraj, S., Deepak, K., Raghavan, V., Kunchukuttan, A., Kumar, P., & Khapra, M. S. (2022). Samanantar: The largest publicly available parallel corpora collection for 11 Indic languages. Transactions of the Association for Computational Linguistics, 10, 145\u2013162.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"9859_CR28","doi-asserted-by":"crossref","unstructured":"Riley, P., Caswell, I., Freitag, M., & Grangier, D. (2019). Translationese as a language in\" multilingual\" nmt. arXiv preprint arXiv:1911.03823.","DOI":"10.18653\/v1\/2020.acl-main.691"},{"key":"9859_CR29","unstructured":"\u0160IGUT, P. (2023). Evaluation of machine-generated text detectors."},{"key":"9859_CR30","unstructured":"Siripragada, S., Philip, J., Namboodiri, V. P., & Jawahar, C. V. (2020). A multilingual parallel corpora collection effort for indian languages. arXiv preprint arXiv:2007.07691."},{"key":"9859_CR31","unstructured":"Tiedemann, J. (2020). The tatoeba translation challenge-realistic data sets for low resource and multilingual mt. In Proceedings of the Fifth Conference on Machine Translation, 1174\u20131182."},{"key":"9859_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, M., & Toral, A. (2019). The effect of translationese in machine translation test sets. arXiv preprint arXiv:1906.08069.","DOI":"10.18653\/v1\/W19-5208"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-025-09859-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10579-025-09859-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-025-09859-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T05:14:41Z","timestamp":1765257281000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10579-025-09859-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,6]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["9859"],"URL":"https:\/\/doi.org\/10.1007\/s10579-025-09859-8","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"type":"print","value":"1574-020X"},{"type":"electronic","value":"1574-0218"}],"subject":[],"published":{"date-parts":[[2025,9,6]]},"assertion":[{"value":"30 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"None.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}