{"id":"https://openalex.org/W2739853973","doi":"https://doi.org/10.18653/v1/w17-0811","title":"Word Similarity Datasets for Indian Languages: Annotation and Baseline Systems","display_name":"Word Similarity Datasets for Indian Languages: Annotation and Baseline Systems","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2739853973","doi":"https://doi.org/10.18653/v1/w17-0811","mag":"2739853973"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-0811","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-0811","pdf_url":"https://www.aclweb.org/anthology/W17-0811.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 11th Linguistic Annotation Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-0811.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014350149","display_name":"Syed Sarfaraz Akhtar","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Syed Sarfaraz Akhtar","raw_affiliation_strings":["International Institute of Information Technology Hyderabad, Telangana, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068152205","display_name":"Arihant Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arihant Gupta","raw_affiliation_strings":["International Institute of Information Technology Hyderabad, Telangana, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011376720","display_name":"Avijit Vajpayee","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Avijit Vajpayee","raw_affiliation_strings":["International Institute of Information Technology Hyderabad, Telangana, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001920631","display_name":"Arjit Srivastava","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arjit Srivastava","raw_affiliation_strings":["International Institute of Information Technology Hyderabad, Telangana, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013675579","display_name":"Manish Shrivastava","orcid":"https://orcid.org/0000-0001-8705-6637"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manish Shrivastava","raw_affiliation_strings":["International Institute of Information Technology Hyderabad, Telangana, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014350149"],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":1.3652,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.85825798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9819999933242798,"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/baseline","display_name":"Baseline (sea)","score":0.8088576793670654},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7518168687820435},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7393229603767395},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6801226139068604},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6497522592544556},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6259544491767883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5239382386207581},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36793872714042664},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20621055364608765}],"concepts":[{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.8088576793670654},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7518168687820435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7393229603767395},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6801226139068604},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6497522592544556},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6259544491767883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5239382386207581},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36793872714042664},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20621055364608765},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-0811","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-0811","pdf_url":"https://www.aclweb.org/anthology/W17-0811.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 11th Linguistic Annotation Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-0811","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-0811","pdf_url":"https://www.aclweb.org/anthology/W17-0811.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 11th Linguistic Annotation Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2739853973.pdf","grobid_xml":"https://content.openalex.org/works/W2739853973.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W92502657","https://openalex.org/W130850236","https://openalex.org/W1614298861","https://openalex.org/W1633328346","https://openalex.org/W1654370055","https://openalex.org/W1854884267","https://openalex.org/W2053921957","https://openalex.org/W2067438047","https://openalex.org/W2070150502","https://openalex.org/W2080100102","https://openalex.org/W2091494174","https://openalex.org/W2102131037","https://openalex.org/W2103318667","https://openalex.org/W2126725946","https://openalex.org/W2133280805","https://openalex.org/W2133436118","https://openalex.org/W2141599568","https://openalex.org/W2141799614","https://openalex.org/W2251687199","https://openalex.org/W2251874715","https://openalex.org/W2252106004","https://openalex.org/W2493916176","https://openalex.org/W2950577311"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W38394648","https://openalex.org/W2062849642","https://openalex.org/W2038246283","https://openalex.org/W2999699891","https://openalex.org/W2394602299","https://openalex.org/W2951029798","https://openalex.org/W2435130738","https://openalex.org/W2349125667","https://openalex.org/W2157036556"],"abstract_inverted_index":{"With":[0],"the":[1,18,21,58],"advent":[2],"of":[3,20,34,60,70,74],"word":[4,6,31,71,82,99],"representations,":[5],"similarity":[7,32,72,100],"tasks":[8],"are":[9,47],"becoming":[10],"increasing":[11],"popular":[12],"as":[13],"an":[14],"evaluation":[15],"metric":[16],"for":[17,81,88],"quality":[19],"representations.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"present":[27,78],"manually":[28],"annotated":[29],"monolingual":[30],"datasets":[33,73],"six":[35],"Indian":[36,50],"languages":[37,46,51],"-Urdu,":[38],"Telugu,":[39],"Marathi,":[40],"Punjabi,":[41],"Tamil":[42],"and":[43,55,68,91],"Gujarati.":[44],"These":[45],"most":[48],"spoken":[49],"worldwide":[52],"after":[53],"Hindi":[54],"Bengali.":[56],"For":[57],"construction":[59],"these":[61],"datasets,":[62],"our":[63],"approach":[64],"relies":[65],"on":[66,96],"translation":[67],"re-annotation":[69],"English.":[75],"We":[76],"also":[77],"baseline":[79],"scores":[80],"representation":[83],"models":[84],"using":[85],"state-of-the-art":[86],"techniques":[87],"Urdu,":[89],"Telugu":[90],"Marathi":[92],"by":[93],"evaluating":[94],"them":[95],"newly":[97],"created":[98],"datasets.":[101]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
