{"id":"https://openalex.org/W3194729942","doi":"https://doi.org/10.1145/3469096.3469864","title":"Searching harsh documents","display_name":"Searching harsh documents","publication_year":2021,"publication_date":"2021-08-16","ids":{"openalex":"https://openalex.org/W3194729942","doi":"https://doi.org/10.1145/3469096.3469864","mag":"3194729942"},"language":"en","primary_location":{"id":"doi:10.1145/3469096.3469864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469096.3469864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Symposium on Document Engineering","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/A5062591304","display_name":"Ophir Frieder","orcid":"https://orcid.org/0000-0001-5076-8171"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ophir Frieder","raw_affiliation_strings":["Georgetown University"],"affiliations":[{"raw_affiliation_string":"Georgetown University","institution_ids":["https://openalex.org/I184565670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062591304"],"corresponding_institution_ids":["https://openalex.org/I184565670"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11354553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9602000117301941,"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/T10028","display_name":"Topic Modeling","score":0.9602000117301941,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9563999772071838,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9473999738693237,"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/computer-science","display_name":"Computer science","score":0.8214821219444275},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6640366911888123},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6173031330108643},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.568318247795105},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5231841206550598},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.495730996131897},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.46800318360328674},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3852870464324951},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3724512755870819},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09519204497337341},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06491425633430481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8214821219444275},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6640366911888123},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6173031330108643},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.568318247795105},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5231841206550598},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.495730996131897},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.46800318360328674},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3852870464324951},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3724512755870819},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09519204497337341},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06491425633430481},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3469096.3469864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469096.3469864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2370831213","https://openalex.org/W4315704968","https://openalex.org/W4285478380","https://openalex.org/W2100255360","https://openalex.org/W2032810564","https://openalex.org/W2107506952","https://openalex.org/W3135287016"],"abstract_inverted_index":{"Conventional,":[0],"textual":[1],"document":[2,39],"search":[3,37,84,91],"is":[4,34],"arguably":[5],"well":[6],"understood.":[7],"Traditional":[8],"and":[9,17,71,80,110],"modern":[10],"(neural)":[11],"algorithms":[12],"are":[13,20,26,48,51,56,60,63,94],"available;":[14],"benchmark":[15],"collections":[16,42],"evaluation":[18,104],"metrics":[19],"prevalent.":[21],"However,":[22],"not":[23,57],"all":[24],"documents":[25,46],"conventional":[27],"or":[28,62,97],"purely":[29],"textual.":[30],"We":[31,67,76,86,99,118],"explore":[32],"what":[33],"takes":[35],"to":[36,116],"\"harsh\"":[38],"collections.":[40],"Such":[41],"comprise":[43],"potentially":[44],"of":[45,90,105],"that":[47,55,93],"natively":[49],"non-digital,":[50],"multilingual,":[52],"include":[53],"components":[54],"strictly":[58],"textual,":[59],"corrupted,":[61],"a":[64,83,121],"combination":[65],"thereof.":[66],"address":[68],"machine":[69],"readability":[70],"its":[72],"implication":[73],"on":[74,102,124],"search.":[75],"overview":[77],"component":[78],"segmentation":[79],"integration":[81],"as":[82],"process.":[85],"describe":[87],"the":[88,103,106],"processing":[89],"queries":[92],"informationally":[95],"deficient":[96],"corrupt.":[98],"then":[100],"comment":[101],"selected":[107],"efforts":[108],"presented":[109],"highlight":[111],"their":[112],"history":[113],"from":[114],"concept":[115],"practice.":[117],"conclude":[119],"with":[120],"brief":[122],"commentary":[123],"ongoing":[125],"efforts.":[126]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}