{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/building-a-word-segmenter-for-sanskrit","title":"Building a Word Segmenter for Sanskrit Overnight","arxiv_id":"1802.06185","date":"2018-02-17","proceeding":"LREC 2018 5","authors":["Vikas Reddy","Amrith Krishna","Vishnu Dutt Sharma","Prateek Gupta","Vineeth M R","Pawan Goyal"],"abstract":"There is an abundance of digitised texts available in Sanskrit. However, the\nword segmentation task in such texts are challenging due to the issue of\n'Sandhi'. In Sandhi, words in a sentence often fuse together to form a single\nchunk of text, where the word delimiter vanishes and sounds at the word\nboundaries undergo transformations, which is also reflected in the written\ntext. Here, we propose an approach that uses a deep sequence to sequence\n(seq2seq) model that takes only the sandhied string as the input and predicts\nthe unsandhied string. The state of the art models are linguistically involved\nand have external dependencies for the lexical and morphological analysis of\nthe input. Our model can be trained \"overnight\" and be used for production. In\nspite of the knowledge lean approach, our system preforms better than the\ncurrent state of the art by gaining a percentage increase of 16.79 % than the\ncurrent state of the art.","url_abs":"http://arxiv.org/abs/1802.06185v1","url_pdf":"http://arxiv.org/pdf/1802.06185v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"building-a-word-segmenter-for-sanskrit","repo_url":"https://github.com/cvikasreddy/skt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"morphological-analysis","task_name":"Morphological Analysis"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}