{"id":"https://openalex.org/W2251696044","doi":"https://doi.org/10.3115/v1/w14-5506","title":"A hybrid approach for automatic clause boundary identification in Hindi","display_name":"A hybrid approach for automatic clause boundary identification in Hindi","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251696044","doi":"https://doi.org/10.3115/v1/w14-5506","mag":"2251696044"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-5506","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5506","pdf_url":"https://aclanthology.org/W14-5506.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 Fifth Workshop on South and Southeast Asian Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-5506.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103065972","display_name":"Rahul Sharma","orcid":"https://orcid.org/0000-0003-1697-3897"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rahul Sharma","raw_affiliation_strings":["Language Technology Research Centre, IIIT-Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Language Technology Research Centre, IIIT-Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100683998","display_name":"Soma Paul","orcid":"https://orcid.org/0000-0002-2504-4419"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soma Paul","raw_affiliation_strings":["Language Technology Research Centre, IIIT-Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Language Technology Research Centre, IIIT-Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103065972"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.4229,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7696175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"49"},"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":0.9995999932289124,"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/T13629","display_name":"Text Readability and Simplification","score":0.987500011920929,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.9462432861328125},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7607600092887878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7504738569259644},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7346435785293579},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7181509733200073},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.708714485168457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.638355016708374},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5547133684158325},{"id":"https://openalex.org/keywords/dependent-clause","display_name":"Dependent clause","score":0.4346494674682617},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3787572681903839},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1403561532497406},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0915994942188263}],"concepts":[{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.9462432861328125},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7607600092887878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504738569259644},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7346435785293579},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7181509733200073},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.708714485168457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.638355016708374},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5547133684158325},{"id":"https://openalex.org/C134510687","wikidata":"https://www.wikidata.org/wiki/Q1122094","display_name":"Dependent clause","level":3,"score":0.4346494674682617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3787572681903839},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1403561532497406},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0915994942188263},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/w14-5506","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5506","pdf_url":"https://aclanthology.org/W14-5506.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 Fifth Workshop on South and Southeast Asian Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.684.3205","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.684.3205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-5506.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-5506","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5506","pdf_url":"https://aclanthology.org/W14-5506.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 Fifth Workshop on South and Southeast Asian Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251696044.pdf","grobid_xml":"https://content.openalex.org/works/W2251696044.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W163922149","https://openalex.org/W767393422","https://openalex.org/W1498277072","https://openalex.org/W1884004694","https://openalex.org/W2055438451","https://openalex.org/W2102626494","https://openalex.org/W2140482227","https://openalex.org/W2141099517","https://openalex.org/W2147880316","https://openalex.org/W2156515921","https://openalex.org/W2167095681","https://openalex.org/W2175053550","https://openalex.org/W2462042662","https://openalex.org/W2746293096","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2384553807","https://openalex.org/W1557888283","https://openalex.org/W3089999372","https://openalex.org/W2265245145","https://openalex.org/W3110423299","https://openalex.org/W4312229285","https://openalex.org/W2738278463","https://openalex.org/W4308939443","https://openalex.org/W4299528489","https://openalex.org/W1915345451"],"abstract_inverted_index":{"A":[0],"complex":[1,13],"sentence,":[2],"divided":[3],"into":[4],"clauses,":[5],"can":[6],"be":[7],"analyzed":[8],"more":[9,49],"easily":[10],"than":[11],"the":[12,19,28],"sentence":[14],"itself.":[15],"We":[16,51],"present":[17],"here,":[18],"task":[20,48],"of":[21,30,66],"clauses":[22],"identification":[23,42,65],"in":[24],"Hindi":[25],"text.":[26],"To":[27],"best":[29],"our":[31],"knowledge,":[32],"not":[33],"much":[34],"work":[35],"has":[36],"been":[37],"done":[38],"on":[39],"clause":[40],"boundary":[41],"for":[43,64],"Hindi,":[44],"which":[45,57],"makes":[46],"this":[47],"important.":[50],"have":[52],"built":[53],"a":[54],"Hybrid":[55],"system":[56],"gives":[58],"90.804%":[59],"F1-scores":[60,63],"and":[61,69],"94.697%":[62],"clauses'":[67],"start":[68],"end":[70],"respectively.":[71]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
