{"id":"https://openalex.org/W2741444903","doi":"https://doi.org/10.18653/v1/w17-2214","title":"A Dataset for Sanskrit Word Segmentation","display_name":"A Dataset for Sanskrit Word Segmentation","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2741444903","doi":"https://doi.org/10.18653/v1/w17-2214","mag":"2741444903"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-2214","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2214","pdf_url":"https://www.aclweb.org/anthology/W17-2214.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Joint SIGHUM Workshop on Computational Linguistics\n          for Cultural Heritage, Social Sciences, Humanities and Literature","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-2214.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108820667","display_name":"Amrith Krishna","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Amrith Krishna","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007677672","display_name":"Pavan Kumar Satuluri","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pavan Kumar Satuluri","raw_affiliation_strings":["Dept. of Computer Science & Engineering, Indian Institute of Technology Kharagpur","School of Linguistics & Literary Studies, Chinmaya Vishwavidyapeeth CEG Campus;"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science & Engineering, Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"School of Linguistics & Literary Studies, Chinmaya Vishwavidyapeeth CEG Campus;","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103213198","display_name":"Pawan Goyal","orcid":"https://orcid.org/0000-0002-9414-8166"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pawan Goyal","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108820667"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1453,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9038572,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sanskrit","display_name":"Sanskrit","score":0.8437340259552002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6752785444259644},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6177094578742981},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.613369345664978},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5939653515815735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5913918614387512},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3896231949329376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34649550914764404},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23912492394447327},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06421157717704773}],"concepts":[{"id":"https://openalex.org/C29912816","wikidata":"https://www.wikidata.org/wiki/Q11059","display_name":"Sanskrit","level":2,"score":0.8437340259552002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6752785444259644},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6177094578742981},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.613369345664978},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5939653515815735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5913918614387512},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3896231949329376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34649550914764404},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23912492394447327},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06421157717704773}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-2214","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2214","pdf_url":"https://www.aclweb.org/anthology/W17-2214.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Joint SIGHUM Workshop on Computational Linguistics\n          for Cultural Heritage, Social Sciences, Humanities and Literature","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-2214","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2214","pdf_url":"https://www.aclweb.org/anthology/W17-2214.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Joint SIGHUM Workshop on Computational Linguistics\n          for Cultural Heritage, Social Sciences, Humanities and Literature","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741444903.pdf","grobid_xml":"https://content.openalex.org/works/W2741444903.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W646974955","https://openalex.org/W1493799397","https://openalex.org/W1513168562","https://openalex.org/W2029249040","https://openalex.org/W2108980486","https://openalex.org/W2122228338","https://openalex.org/W2125910575","https://openalex.org/W2132022337","https://openalex.org/W2166416461","https://openalex.org/W2250511639","https://openalex.org/W2251444172","https://openalex.org/W2469279958","https://openalex.org/W2524182563","https://openalex.org/W2538747984","https://openalex.org/W2574685885","https://openalex.org/W2576240207","https://openalex.org/W2789474247","https://openalex.org/W2952099486"],"related_works":["https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2159591557","https://openalex.org/W2785359773","https://openalex.org/W2058548953","https://openalex.org/W2385598138","https://openalex.org/W2366925922"],"abstract_inverted_index":{"The":[0],"last":[1],"decade":[2],"saw":[3],"a":[4,115],"surge":[5],"in":[6,12,33,40,55,62,68,100,111,126],"digitisation":[7],"efforts":[8],"for":[9,37,44,58,90,120,150],"ancient":[10],"manuscripts":[11],"Sanskrit.":[13,34],"Due":[14],"to":[15,20,97,104],"various":[16],"linguistic":[17,161],"peculiarities":[18],"inherent":[19],"the":[21,24,51,79,85,88,91,101,106,127,131,146,151,160,166,170],"language,":[22],"even":[23],"preliminary":[25],"tasks":[26],"such":[27],"as":[28],"word":[29,56,92,121],"segmentation":[30,57,93],"are":[31,42],"non-trivial":[32],"Elegant":[35],"models":[36],"Word":[38],"Segmentation":[39],"Sanskrit":[41],"indispensable":[43],"further":[45],"syntactic":[46],"and":[47,71,87,103,108,138,141],"semantic":[48],"processing":[49],"of":[50,117,169],"manuscripts.":[52],"Current":[53],"works":[54],"Sanskrit,":[59],"though":[60],"commendable":[61],"their":[63,69],"novelty,":[64],"often":[65],"have":[66],"variations":[67],"objective":[70],"evaluation":[72],"criteria.":[73],"In":[74,95,154],"this":[75,155],"work,":[76,156],"we":[77,113,129,157],"set":[78],"record":[80],"straight.":[81],"We":[82],"formally":[83],"define":[84],"objectives":[86],"requirements":[89],"task.":[94],"order":[96],"encourage":[98],"research":[99],"field":[102],"alleviate":[105],"time":[107],"effort":[109],"required":[110],"pre-processing,":[112],"release":[114],"dataset":[116,128],"115,000":[118],"sentences":[119],"segmentation.":[122],"For":[123],"each":[124],"sentence":[125],"include":[130],"input":[132],"character":[133],"sequence,":[134],"ground":[135],"truth":[136],"segmentation,":[137],"additionally":[139],"lexical":[140],"morphological":[142],"information":[143],"about":[144],"all":[145],"phonetically":[147],"possible":[148,171],"segments":[149],"given":[152],"sentence.":[153],"also":[158],"discuss":[159],"considerations":[162],"made":[163],"while":[164],"generating":[165],"candidate":[167],"space":[168],"segments.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}