{"id":"https://openalex.org/W3214042884","doi":"https://doi.org/10.18653/v1/2021.nllp-1.12","title":"Searching for Legal Documents at Paragraph Level: Automating Label Generation and Use of an Extended Attention Mask for Boosting Neural Models of Semantic Similarity","display_name":"Searching for Legal Documents at Paragraph Level: Automating Label Generation and Use of an Extended Attention Mask for Boosting Neural Models of Semantic Similarity","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3214042884","doi":"https://doi.org/10.18653/v1/2021.nllp-1.12","mag":"3214042884"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.nllp-1.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.nllp-1.12","pdf_url":"https://aclanthology.org/2021.nllp-1.12.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 Natural Legal Language Processing Workshop 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2021.nllp-1.12.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010582486","display_name":"Li Tang","orcid":"https://orcid.org/0000-0001-7412-5808"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Li Tang","raw_affiliation_strings":["Institute of Computational Linguistics","Institute of Computational Linguistics University of Zurich University of Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Linguistics","institution_ids":[]},{"raw_affiliation_string":"Institute of Computational Linguistics University of Zurich University of Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073027507","display_name":"Simon Clematide","orcid":"https://orcid.org/0000-0003-1365-0662"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Simon Clematide","raw_affiliation_strings":["Institute of Computational Linguistics","Institute of Computational Linguistics University of Zurich University of Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Linguistics","institution_ids":[]},{"raw_affiliation_string":"Institute of Computational Linguistics University of Zurich University of Zurich","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010582486"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"114","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9965999722480774,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social 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":0.8298859000205994},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.6516493558883667},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6470950841903687},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6379714012145996},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5614646673202515},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5043238401412964},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.48960787057876587},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45582684874534607},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45249882340431213},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.4522847831249237},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4232298731803894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.1597164273262024},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12174180150032043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8298859000205994},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.6516493558883667},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6470950841903687},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6379714012145996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5614646673202515},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5043238401412964},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.48960787057876587},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45582684874534607},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45249882340431213},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.4522847831249237},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4232298731803894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.1597164273262024},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12174180150032043},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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":3,"locations":[{"id":"doi:10.18653/v1/2021.nllp-1.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.nllp-1.12","pdf_url":"https://aclanthology.org/2021.nllp-1.12.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 Natural Legal Language Processing Workshop 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:www.zora.uzh.ch:216067","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Tang, Li; Clematide, Simon (2021). Searching for Legal Documents at Paragraph Level: Automating Label Generation and Use of an Extended Attention Mask for Boosting Neural Models of Semantic Similarity. In: Proceedings of the Natural Legal Language Processing Workshop 2021, Punta Cana, Dominican Republic, 10 November 2021. Association for Computational Linguistics, 114-122.","raw_type":"Conference or Workshop Item"},{"id":"doi:10.5167/uzh-216067","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-216067","pdf_url":null,"source":{"id":"https://openalex.org/S7407051291","display_name":"Universit\u00e4t Z\u00fcrich, ZORA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.nllp-1.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.nllp-1.12","pdf_url":"https://aclanthology.org/2021.nllp-1.12.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 Natural Legal Language Processing Workshop 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3214042884.pdf","grobid_xml":"https://content.openalex.org/works/W3214042884.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W40010561","https://openalex.org/W1532325895","https://openalex.org/W1970859146","https://openalex.org/W1984052055","https://openalex.org/W2009751122","https://openalex.org/W2045660975","https://openalex.org/W2102549231","https://openalex.org/W2111903956","https://openalex.org/W2131744502","https://openalex.org/W2146936057","https://openalex.org/W2149880985","https://openalex.org/W2407715102","https://openalex.org/W2510940142","https://openalex.org/W2593088329","https://openalex.org/W2794557536","https://openalex.org/W2923014074","https://openalex.org/W2963310665","https://openalex.org/W2964165804","https://openalex.org/W2991316439","https://openalex.org/W3000429004","https://openalex.org/W3018407395","https://openalex.org/W3034707327","https://openalex.org/W3034972497","https://openalex.org/W3035668167","https://openalex.org/W3043016077","https://openalex.org/W3081663193","https://openalex.org/W3099950029","https://openalex.org/W3102561203","https://openalex.org/W3124923911"],"related_works":["https://openalex.org/W2377059580","https://openalex.org/W127000293","https://openalex.org/W4200355488","https://openalex.org/W3215892509","https://openalex.org/W2928616779","https://openalex.org/W2412592434","https://openalex.org/W2010523086","https://openalex.org/W2086485446","https://openalex.org/W2135511601","https://openalex.org/W2170543300"],"abstract_inverted_index":{"Searching":[0],"for":[1,13,21,133,141,158],"legal":[2,36],"documents":[3],"is":[4,11],"a":[5,30,39,47,54,95,138,166],"specialized":[6],"Information":[7],"Retrieval":[8],"task":[9,96],"that":[10,116,179,194],"relevant":[12,77],"expert":[14],"users":[15],"(lawyers":[16],"and":[17,20,110,120,143,147],"their":[18],"assistants)":[19],"non-expert":[22],"users.":[23],"By":[24],"searching":[25],"previous":[26],"court":[27],"decisions":[28],"(cases),":[29],"user":[31],"can":[32,79,186],"better":[33],"prepare":[34],"the":[35,84,118,121,128,198],"reasoning":[37],"of":[38,53,101,130],"new":[40],"case.":[41],"Being":[42],"able":[43],"to":[44,60,97,152],"search":[45,122],"using":[46,108,165],"natural":[48],"language":[49],"text":[50],"snippet":[51],"instead":[52],"more":[55,76],"artificial":[56],"query":[57,62,85,119],"could":[58,69],"help":[59],"prevent":[61],"formulation":[63],"issues.":[64],"Also,":[65],"if":[66,83],"semantic":[67,103,160,180],"similarity":[68,104,132,161,168,181],"be":[70,80,187],"modeled":[71],"beyond":[72],"exact":[73],"lexical":[74],"matches,":[75],"results":[78,134],"found":[81],"even":[82],"terms":[86],"don't":[87],"match":[88],"exactly.":[89],"For":[90],"this":[91,175],"domain,":[92],"we":[93,154,177],"formulated":[94],"compare":[98],"different":[99,172],"ways":[100],"modeling":[102,182],"at":[105,162],"paragraph":[106,163],"level,":[107,164],"neural":[109,184],"non-neural":[111],"systems.":[112],"We":[113],"compared":[114],"systems":[115,173,185],"encode":[117],"collection":[123],"paragraphs":[124],"as":[125],"vectors,":[126],"enabling":[127],"use":[129],"cosine":[131],"ranking.":[135],"After":[136],"building":[137],"German":[139],"dataset":[140],"cases":[142,151],"statutes":[144],"from":[145,150],"Switzerland,":[146],"extracting":[148],"citations":[149],"statutes,":[153],"developed":[155],"an":[156,190],"algorithm":[157],"estimating":[159],"linkbased":[167],"method.":[169],"When":[170],"evaluating":[171],"in":[174,197],"way,":[176],"find":[178],"by":[183],"boosted":[188],"with":[189],"extended":[191],"attention":[192],"mask":[193],"quenches":[195],"noise":[196],"inputs.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}