{"id":"https://openalex.org/W2963961468","doi":"https://doi.org/10.1145/3322640.3326713","title":"A Regularization Approach to Combining Keywords and Training Data in Technology-Assisted Review","display_name":"A Regularization Approach to Combining Keywords and Training Data in Technology-Assisted Review","publication_year":2019,"publication_date":"2019-06-17","ids":{"openalex":"https://openalex.org/W2963961468","doi":"https://doi.org/10.1145/3322640.3326713","mag":"2963961468"},"language":"en","primary_location":{"id":"doi:10.1145/3322640.3326713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3322640.3326713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law","raw_type":"proceedings-article"},"type":"conference-paper","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/A5062016266","display_name":"Eugene Yang","orcid":"https://orcid.org/0000-0002-0051-1535"},"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":false,"raw_author_name":"Eugene Yang","raw_affiliation_strings":["IR Lab, Georgetown University, Washington, DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IR Lab, Georgetown University, Washington, DC, USA","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020081385","display_name":"David Lewis","orcid":"https://orcid.org/0000-0002-3503-4644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David D. Lewis","raw_affiliation_strings":["Cyxtera Technologies, Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cyxtera Technologies, Dallas, TX, USA","institution_ids":[]}]},{"author_position":"last","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":false,"raw_author_name":"Ophir Frieder","raw_affiliation_strings":["IR Lab, Georgetown University, Washington, DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IR Lab, Georgetown University, Washington, DC, USA","institution_ids":["https://openalex.org/I184565670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6561,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.74663351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.9987000226974487,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9969000220298767,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8049402832984924},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5815054774284363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5741989016532898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5363951921463013},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4428463876247406},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.41084539890289307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8049402832984924},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5815054774284363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5741989016532898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5363951921463013},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4428463876247406},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.41084539890289307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3322640.3326713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3322640.3326713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W144973051","https://openalex.org/W607505555","https://openalex.org/W1541527977","https://openalex.org/W1594962278","https://openalex.org/W1700671489","https://openalex.org/W1850660615","https://openalex.org/W1890144115","https://openalex.org/W1990381576","https://openalex.org/W2010526612","https://openalex.org/W2029075138","https://openalex.org/W2040066835","https://openalex.org/W2043566294","https://openalex.org/W2083605078","https://openalex.org/W2091825929","https://openalex.org/W2094144755","https://openalex.org/W2104640308","https://openalex.org/W2107438106","https://openalex.org/W2111310810","https://openalex.org/W2118585731","https://openalex.org/W2121402967","https://openalex.org/W2122825543","https://openalex.org/W2131148434","https://openalex.org/W2150102617","https://openalex.org/W2166183437","https://openalex.org/W2749448933","https://openalex.org/W2776313241","https://openalex.org/W2799002609","https://openalex.org/W2799108077","https://openalex.org/W2897178939","https://openalex.org/W2913535645","https://openalex.org/W2951781666","https://openalex.org/W2997591727","https://openalex.org/W3013164143","https://openalex.org/W4244393449","https://openalex.org/W6677656871"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Manual":[0],"keyword":[1,37],"queries":[2],"and":[3,23,83,121,127],"supervised":[4],"learning":[5,43,123],"(technology-assisted":[6],"review)":[7],"have":[8],"been":[9],"viewed":[10],"as":[11,20,39],"conflicting":[12],"approaches":[13,143],"to":[14],"high":[15],"recall":[16],"retrieval":[17,93],"tasks":[18],"(such":[19],"civil":[21],"discovery":[22],"sunshine":[24],"law":[25],"requests)":[26],"in":[27,90],"the":[28,59,105],"law.":[29],"We":[30,68],"propose":[31],"a":[32,36,40,44,110],"synthesis":[33],"that":[34,71,104,141],"uses":[35],"list":[38],"regularizer":[41],"when":[42],"logistic":[45],"regression":[46],"model":[47],"from":[48,75,118],"labeled":[49],"examples.":[50],"Balancing":[51],"keywords":[52,126],"against":[53],"training":[54,65,128],"data":[55,100,129],"requires":[56],"knowing":[57],"how":[58],"regularization":[60],"penalty":[61],"should":[62],"scale":[63],"with":[64],"set":[66],"size.":[67],"show,":[69],"however,":[70],"advice":[72],"on":[73,97,133],"scaling":[74],"theory":[76],"is":[77,88,113],"contradictory,":[78],"software":[79],"defaults":[80],"are":[81],"inconsistent,":[82],"standard":[84],"practice":[85],"(validation-based":[86],"tuning)":[87],"impractical":[89],"many":[91],"high-recall":[92],"settings.":[94],"Through":[95],"experiments":[96],"simulated":[98],"e-discovery":[99],"sets,":[101],"we":[102],"show":[103],"penalization":[106],"scheme":[107],"suggested":[108],"by":[109],"Bayesian":[111],"interpretation":[112],"substantially":[114],"safer":[115],"than":[116,136],"alternatives":[117],"stochastic":[119],"optimization":[120],"computational":[122],"theory.":[124],"Combining":[125],"provides":[130],"better":[131],"effectiveness":[132],"our":[134],"datasets":[135],"using":[137],"either":[138],"alone,":[139],"showing":[140],"both":[142],"bring":[144],"value.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}