{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T04:38:22Z","timestamp":1758083902080,"version":"3.44.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032046260"},{"type":"electronic","value":"9783032046277"}],"license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/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":[[2026]]},"DOI":"10.1007\/978-3-032-04627-7_4","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:07:19Z","timestamp":1757988439000},"page":"60-76","update-policy":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Unified Attention-Based Model for\u00a0Segmenting Compound Words in\u00a0Sanskrit"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0009-0008-1664-5125","authenticated-orcid":false,"given":"Irfan","family":"Ali","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0003-0833-4403","authenticated-orcid":false,"given":"Liliana Lo","family":"Presti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0003-0304-0764","authenticated-orcid":false,"given":"Igor","family":"Spano\u2019","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0002-8766-6395","authenticated-orcid":false,"given":"Marco La","family":"Cascia","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Krishna, A., Satuluri, P., Goyal, P.: A dataset for Sanskrit word segmentation. In: Proceedings of the Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pp. 105\u2013114 (2017)","DOI":"10.18653\/v1\/W17-2214"},{"key":"4_CR2","unstructured":"Krishnan, S., Kulkarni, A., Huet, G.: Validation and normalization of DCS corpus using Sanskrit heritage tools to build a tagged gold corpus. arXiv preprint arXiv:2005.06545 (2020)"},{"issue":"4","key":"4_CR3","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1017\/S0956796804005416","volume":"15","author":"G Huet","year":"2005","unstructured":"Huet, G.: A functional toolkit for morphological and phonological processing, application to a Sanskrit tagger. J. Funct. Program. 15(4), 573\u2013614 (2005)","journal-title":"J. Funct. Program."},{"issue":"1\u20134","key":"4_CR4","first-page":"169","volume":"70","author":"A Kulkarni","year":"2009","unstructured":"Kulkarni, A., Shukl, D.: Sanskrit morphological analyser: some issues. Indian Linguist. 70(1\u20134), 169\u2013177 (2009)","journal-title":"Indian Linguist."},{"key":"4_CR5","unstructured":"Natarajan, A., Charniak, E.: S3-statistical Sandhi splitting. In: Proceedings of 5th International Joint Conference on Natural Language Processing, pp. 301\u2013308 (2011)"},{"key":"4_CR6","unstructured":"Krishna, A., et al.: Word segmentation in Sanskrit using path constrained random walks. In: Proceedings of COLING 2016, 26th International Conference on Computational Linguistics: Technical Papers, pp. 494\u2013504 (2016)"},{"key":"4_CR7","unstructured":"Hellwig, O.: Using recurrent neural networks for joint compound splitting and Sandhi resolution in Sanskrit. In: 4th Biennial Workshop on Less-Resourced Languages (2015)"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Ali, I., Lo Presti, L., Spano, I., La Cascia, M.: ABBIE: attention-based BI-encoders for predicting where to split compound Sanskrit words. In: Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2 (2025)","DOI":"10.5220\/0013155300003890"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Sandhan, J., Singha, R., Rao, N., Samanta, S., Behera, L., Goyal, P.: TransLIST: a transformer-based linguistically informed Sanskrit tokenizer. arXiv preprint arXiv:2210.11753 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.513"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Nehrdich, S., Hellwig, O., Keutzer, K.: One model is all you need: ByT5-Sanskrit, a unified model for Sanskrit NLP tasks. arXiv preprint arXiv:2409.13920 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.805"},{"key":"4_CR11","unstructured":"Bhatt, K., Ramakrishnan, G., Jyothi, P.: CharSS: character-level transformer model for Sanskrit word segmentation. arXiv preprint arXiv:2407.06331 (2024)"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Lyu, C., Zhang, Y., Ji, D.: Joint word segmentation, POS-tagging and syntactic chunking. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) (2016)","DOI":"10.1609\/aaai.v30i1.10369"},{"key":"4_CR13","unstructured":"Li, J., Girrbach, L.: Word segmentation and morphological parsing for Sanskrit. arXiv preprint arXiv:2201.12833 (2022)"},{"issue":"1","key":"4_CR14","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/34.824820","volume":"22","author":"G Nagy","year":"2000","unstructured":"Nagy, G.: Twenty years of document image analysis in PAMI. IEEE Trans. Pattern Anal. Mach. Intell. 22(1), 38\u201362 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR15","unstructured":"Goyal, P., Huet, G., Kulkarni, A., Scharf, P., Bunker, R.: A collaborative platform for Sanskrit processing. In: Proceedings of the 24th Computational Linguistics Conference, pp. 1011\u20131028 (2012)"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, A., Krishna, A., Goyal, P., Hellwig, O.: Evaluating neural morphological taggers for Sanskrit. arXiv preprint arXiv:2005.10893 (2020)","DOI":"10.18653\/v1\/2020.sigmorphon-1.23"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Tsarfaty, R., Bareket, D., Klein, S., Seker, A.: From SPMRL to NMRL: what did we learn (and unlearn) in a decade of parsing morphologically-rich languages (MRLs)? arXiv preprint arXiv:2005.01330 (2020)","DOI":"10.18653\/v1\/2020.acl-main.660"},{"issue":"2","key":"4_CR18","first-page":"145","volume":"4","author":"P Goyal","year":"2016","unstructured":"Goyal, P., Huet, G.: Design and analysis of a lean interface for Sanskrit corpus annotation. J. Lang. Model. 4(2), 145\u2013182 (2016)","journal-title":"J. Lang. Model."},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Dave, S., Singh, A.K., Prathosh, A.P., Lall, B.: Neural compound-word (Sandhi) generation and splitting in Sanskrit language. In: Proceedings of the 3rd ACM India Joint International Conference on Data Science and Management of Data (8th ACM IKDD CODS and 26th COMAD), pp. 171\u2013177 (2021)","DOI":"10.1145\/3430984.3431025"},{"issue":"8","key":"4_CR20","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"4_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 30 (2017)"},{"key":"4_CR22","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 27 (2014)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Haruechaiyasak, C., Kongyoung, S., Dailey, M.: A comparative study on Thai word segmentation approaches. In: 5th International Conference on Electrical Engineering\/Electronics, Computer, Telecommunications and Information Technology (ECTI), vol. 1, pp. 125-128. IEEE (2008)","DOI":"10.1109\/ECTICON.2008.4600388"},{"key":"4_CR24","unstructured":"Hellwig, O.: The Digital Corpus of Sanskrit (DCS) (2010\u20132021)"},{"key":"4_CR25","unstructured":"Learn Sanskrit: Sanscript: Sanskrit transliteration. https:\/\/linproxy.fan.workers.dev:443\/https\/www.learnsanskrit.org. Accessed 08 Aug 2024"},{"key":"4_CR26","unstructured":"Sanskrit Computational Linguistics: Sanskrit computational linguistics (2002\u20132024)"},{"key":"4_CR27","unstructured":"Kumar, S.: Sandhi splitter and analyzer for Sanskrit (with reference to Ac Sandhi). Submitted (2007)"},{"key":"4_CR28","unstructured":"Sanskrit Computational Linguistics. https:\/\/linproxy.fan.workers.dev:443\/https\/sanskrit.uohyd.ac.in\/scl\/. Accessed 08 Aug 2024"},{"key":"4_CR29","unstructured":"INRIA Sanskrit Dictionary. https:\/\/linproxy.fan.workers.dev:443\/https\/sanskrit.inria.fr\/DICO\/reader.en.html. Accessed 08 Aug 2024"},{"key":"4_CR30","unstructured":"Cardona, G.: P\u0101nini: A Survey of Research. Motilal Banarsidass (1997)"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Aralikatte, R., Gantayat, N., Panwar, N., Sankaran, A., Mani, S.: Sanskrit Sandhi splitting using seq2(seq)2 . arXiv preprint arXiv:1801.00428 (2018)","DOI":"10.18653\/v1\/D18-1530"},{"issue":"2","key":"4_CR32","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","volume":"1","author":"RJ Williams","year":"1989","unstructured":"Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1(2), 270\u2013280 (1989)","journal-title":"Neural Comput."}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04627-7_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:07:27Z","timestamp":1757988447000},"score":1,"resource":{"primary":{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/link.springer.com\/10.1007\/978-3-032-04627-7_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032046260","9783032046277"],"references-count":32,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1007\/978-3-032-04627-7_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"16 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/linproxy.fan.workers.dev:443\/https\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}