{"id":"https://openalex.org/W2798010889","doi":"https://doi.org/10.1145/3197026.3197048","title":"Machine Learning vs. Rules and Out-of-the-Box vs. Retrained","display_name":"Machine Learning vs. Rules and Out-of-the-Box vs. Retrained","publication_year":2018,"publication_date":"2018-05-23","ids":{"openalex":"https://openalex.org/W2798010889","doi":"https://doi.org/10.1145/3197026.3197048","mag":"2798010889"},"language":"en","primary_location":{"id":"doi:10.1145/3197026.3197048","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3197026.3197048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries","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/A5061634863","display_name":"Dominika Tkaczyk","orcid":"https://orcid.org/0000-0001-5055-7876"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Dominika Tkaczyk","raw_affiliation_strings":["ADAPT Centre, Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"ADAPT Centre, Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105462536","display_name":"Andrew Collins","orcid":"https://orcid.org/0000-0002-0649-7391"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Andrew Collins","raw_affiliation_strings":["ADAPT Centre, Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"ADAPT Centre, Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110791714","display_name":"P\u00e1raic Sheridan","orcid":null},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Paraic Sheridan","raw_affiliation_strings":["ADAPT Centre, Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"ADAPT Centre, Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081348430","display_name":"Joeran Beel","orcid":"https://orcid.org/0000-0002-4537-5573"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Joeran Beel","raw_affiliation_strings":["ADAPT Centre, Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"ADAPT Centre, Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061634863"],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":3.7463,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.94486324,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"99","last_page":"108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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":0.996399998664856,"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":0.994700014591217,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9937000274658203,"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":0.8738431930541992},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8608167767524719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6737208366394043},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5428860187530518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5320512056350708},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5134738087654114},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5003693103790283},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.45649969577789307},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4555578827857971},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36458268761634827},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10388639569282532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8738431930541992},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8608167767524719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6737208366394043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5428860187530518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5320512056350708},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5134738087654114},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5003693103790283},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.45649969577789307},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4555578827857971},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36458268761634827},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10388639569282532},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3197026.3197048","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3197026.3197048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1407468974","display_name":null,"funder_award_id":"713567","funder_id":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020"},{"id":"https://openalex.org/G2693890202","display_name":null,"funder_award_id":"13/RC/2016","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320335254","display_name":"Horizon 2020","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W55209040","https://openalex.org/W791527587","https://openalex.org/W1015675232","https://openalex.org/W1559499673","https://openalex.org/W1603719052","https://openalex.org/W1606010589","https://openalex.org/W1761420992","https://openalex.org/W1965496623","https://openalex.org/W1969684232","https://openalex.org/W1981159958","https://openalex.org/W1984250866","https://openalex.org/W1991869139","https://openalex.org/W1995577199","https://openalex.org/W2000731427","https://openalex.org/W2018027932","https://openalex.org/W2018295102","https://openalex.org/W2025600322","https://openalex.org/W2040693788","https://openalex.org/W2061598441","https://openalex.org/W2076372024","https://openalex.org/W2118546141","https://openalex.org/W2127484150","https://openalex.org/W2130371208","https://openalex.org/W2137507520","https://openalex.org/W2148251896","https://openalex.org/W2158789913","https://openalex.org/W2163737492","https://openalex.org/W2169089330","https://openalex.org/W2207070065","https://openalex.org/W2295508865","https://openalex.org/W2583061389","https://openalex.org/W2604165577","https://openalex.org/W2604332200","https://openalex.org/W2963112422"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W4381248170","https://openalex.org/W3189621521","https://openalex.org/W2173794830","https://openalex.org/W4287688258","https://openalex.org/W3049211950"],"abstract_inverted_index":{"Bibliographic":[0],"reference":[1,22,46,64,202],"parsing":[2,65],"refers":[3],"to":[4,26,101,106,187],"extracting":[5],"machine-readable":[6],"metadata,":[7],"such":[8],"as":[9],"the":[10,13,15,102,109,171,185,188,193,196],"names":[11],"of":[12,173,201],"authors,":[14],"title,":[16],"or":[17,141],"journal":[18],"name,":[19],"from":[20],"bibliographic":[21],"strings.":[23],"Many":[24,43],"approaches":[25],"this":[27,56],"problem":[28],"have":[29],"been":[30],"proposed":[31],"so":[32],"far,":[33],"including":[34],"regular":[35,142],"expressions,":[36],"knowledge":[37],"bases":[38],"and":[39,61,86,89,98,123,136,229],"supervised":[40],"machine":[41,133,159],"learning.":[42],"open":[44],"source":[45],"parsers":[47,203],"based":[48,138],"on":[49,139,145],"various":[50],"algorithms":[51],"are":[52,75,204],"also":[53,128,181],"available.":[54],"In":[55],"paper,":[57],"we":[58,90],"apply,":[59],"evaluate":[60],"compare":[62,91],"ten":[63],"tools":[66,74,135,137,152,161,175],"in":[67,93,163,170,192,195,205],"a":[68,164],"specific":[69],"business":[70],"use":[71],"case.":[72],"The":[73,198],"Anystyle-Parser,":[76],"Biblio,":[77],"CERMINE,":[78],"Citation,":[79],"Citation-Parser,":[80],"GROBID,":[81],"ParsCit,":[82],"PDFSSA4MET,":[83],"Reference":[84],"Tagger":[85],"Science":[87],"Parse,":[88],"them":[92],"both":[94],"their":[95,210],"out-of-the-box":[96,112,211],"versions":[97,99,200],"tuned":[100],"project-specific":[103],"data.":[104],"According":[105],"our":[107],"evaluation,":[108],"best":[110],"performing":[111],"tool":[113],"is":[114],"GROBID":[115,214],"(F1":[116,121,125],"0.89),":[117,221],"followed":[118],"by":[119,217,224,232],"CERMINE":[120,223],"0.83)":[122],"ParsCit":[124,231],"0.75).":[126,236],"We":[127],"found":[129],"that":[130,183],"even":[131],"though":[132],"learning-based":[134,160],"rules":[140],"expressions":[143],"achieve":[144],"average":[146],"similar":[147],"precision":[148],"(0.77":[149],"for":[150,155,213,222,230],"ML-based":[151],"vs.":[153,177,220,227,235],"0.76":[154],"non-ML-based":[156,174],"tools),":[157],"applying":[158],"results":[162,191],"recall":[165],"three":[166],"times":[167],"higher":[168],"than":[169,209],"case":[172],"(0.66":[176],"0.22).":[178],"Our":[179],"study":[180],"confirms":[182],"tuning":[184],"models":[186],"task-specific":[189],"data":[190],"increase":[194],"quality.":[197],"retrained":[199],"all":[206],"cases":[207],"better":[208],"counterparts;":[212],"F1":[215],"increased":[216],"3%":[218],"(0.92":[219,226],"11%":[225],"0.83),":[228],"16%":[233],"(0.87":[234]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}