{"id":"https://openalex.org/W2822583556","doi":"https://doi.org/10.1145/3209542.3209551","title":"Joint Distributed Representation of Text and Structure of Semi-Structured Documents","display_name":"Joint Distributed Representation of Text and Structure of Semi-Structured Documents","publication_year":2018,"publication_date":"2018-07-03","ids":{"openalex":"https://openalex.org/W2822583556","doi":"https://doi.org/10.1145/3209542.3209551","mag":"2822583556"},"language":"en","primary_location":{"id":"doi:10.1145/3209542.3209551","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209542.3209551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th on Hypertext and Social Media","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102834658","display_name":"Abhishek Laddha","orcid":"https://orcid.org/0000-0002-3607-8366"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Abhishek Laddha","raw_affiliation_strings":["IBM Research, Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089364379","display_name":"Salil Joshi","orcid":"https://orcid.org/0009-0002-8113-7350"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Salil Joshi","raw_affiliation_strings":["American Express Big Data Labs & IBM Research, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"American Express Big Data Labs & IBM Research, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017997182","display_name":"Samiulla Shaikh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Samiulla Shaikh","raw_affiliation_strings":["IBM Research, Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046646390","display_name":"Sameep Mehta","orcid":"https://orcid.org/0000-0002-9599-1526"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sameep Mehta","raw_affiliation_strings":["IBM Research, Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102834658"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":0.3927,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70159733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9930999875068665,"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/T11719","display_name":"Data Quality and Management","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8574944734573364},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6233880519866943},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5255412459373474},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.4793965816497803},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.47744137048721313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4564646780490875},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4290618598461151},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.35822588205337524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8574944734573364},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6233880519866943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5255412459373474},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.4793965816497803},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.47744137048721313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4564646780490875},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4290618598461151},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.35822588205337524},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3209542.3209551","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209542.3209551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th on Hypertext and Social Media","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W172829878","https://openalex.org/W1516184288","https://openalex.org/W1519606823","https://openalex.org/W1614298861","https://openalex.org/W1976022204","https://openalex.org/W1988217119","https://openalex.org/W2015551056","https://openalex.org/W2034797903","https://openalex.org/W2042448356","https://openalex.org/W2045344178","https://openalex.org/W2078206655","https://openalex.org/W2098720114","https://openalex.org/W2107391405","https://openalex.org/W2115613106","https://openalex.org/W2128836931","https://openalex.org/W2131744502","https://openalex.org/W2134222424","https://openalex.org/W2138615112","https://openalex.org/W2153579005","https://openalex.org/W2160196229","https://openalex.org/W2164019165","https://openalex.org/W2250460709","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4376653378","https://openalex.org/W3112765659","https://openalex.org/W2963364736","https://openalex.org/W2808113865","https://openalex.org/W2898077673","https://openalex.org/W4385239468","https://openalex.org/W4200476258","https://openalex.org/W2022470916","https://openalex.org/W2283005578","https://openalex.org/W3002840018"],"abstract_inverted_index":{"Majority":[0],"of":[1,10,16,26,31,74,85,110,144,157,194],"textual":[2],"data":[3,28,139],"over":[4,137],"web":[5,138],"is":[6,186],"in":[7,22,54,127,191],"the":[8,24,27,55,58,77,83,86,93,101,108,142,172,178,181],"form":[9],"semi-structured":[11],"documents.":[12,88],"Thus,":[13],"structural":[14],"skeleton":[15],"such":[17,42,62,114],"documents":[18],"plays":[19],"important":[20],"role":[21],"determining":[23],"semantics":[25,84],"content.":[29],"Presence":[30],"structure":[32,56,79,102],"sometimes":[33],"allows":[34],"us":[35],"to":[36,40,52,80,124,140],"write":[37],"simple":[38],"rules":[39,175],"extract":[41],"information,":[43],"but":[44],"it":[45,203],"may":[46],"not":[47],"be":[48],"always":[49],"possible":[50],"due":[51],"flexibility":[53],"and":[57,76,100,150,174,188,199,211],"frequency":[59],"with":[60,104,207],"which":[61],"structures":[63,111,117],"are":[64,122],"altered.":[65],"In":[66,155],"this":[67],"paper,":[68],"we":[69],"propose":[70],"a":[71],"joint":[72],"modeling":[73],"text":[75,134],"associated":[78,103],"effectively":[81],"capture":[82,177],"semi-structure":[87],"The":[89],"model":[90],"simultaneously":[91],"learns":[92],"dense":[94],"continuous":[95],"representation":[96,146],"for":[97,112,171],"word":[98],"tokens":[99],"them.":[105],"We":[106,130],"utilize":[107],"context":[109,156],"projection":[113],"that":[115,176],"similar":[116,120],"containing":[118],"semantically":[119],"topics":[121],"close":[123],"each":[125],"other":[126,182,212],"vector":[128],"space.":[129],"explore":[131],"two":[132],"semantic":[133,152],"mining":[135],"tasks":[136,163],"test":[141],"effectiveness":[143],"our":[145,184],"viz.,":[147],"document":[148],"similarity,":[149],"table":[151],"component":[153],"identification.":[154],"traditional":[158],"rule-based":[159],"approaches,":[160],"both":[161],"these":[162],"demand":[164],"rich,":[165],"domain-specific":[166],"knowledge":[167,197],"sources,":[168],"homogeneous":[169],"schema":[170],"documents,":[173],"semantics.":[179],"On":[180],"hand,":[183],"approach":[185],"unsupervised":[187,213],"resource":[189],"conscious":[190],"nature.":[192],"Despite":[193],"working":[195],"without":[196],"resources":[198],"large":[200],"training":[201],"data,":[202],"performs":[204],"at":[205],"par":[206],"state-of-the-art":[208],"rule":[209],"based":[210],"approaches.":[214]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}