{"id":"https://openalex.org/W3207482032","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.106","title":"Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference","display_name":"Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3207482032","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.106","mag":"3207482032"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.emnlp-main.106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.106","pdf_url":"https://aclanthology.org/2021.emnlp-main.106.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2021.emnlp-main.106.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055489351","display_name":"William Held","orcid":"https://orcid.org/0000-0003-1410-951X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Held","raw_affiliation_strings":["Department of Computer Science, Stanford University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037853792","display_name":"Dan Iter","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Iter","raw_affiliation_strings":["Department of Computer Science, Stanford University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087088138","display_name":"Dan Jurafsky","orcid":"https://orcid.org/0000-0002-6459-7745"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Jurafsky","raw_affiliation_strings":["Department of Computer Science, Stanford University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055489351"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.7616,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.74494039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1406","last_page":"1417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9957000017166138,"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/coreference","display_name":"Coreference","score":0.9941467642784119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8393604755401611},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6798356175422668},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6723203659057617},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6329708099365234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5952910780906677},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5494609475135803},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4697663486003876},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.44224974513053894}],"concepts":[{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.9941467642784119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8393604755401611},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6798356175422668},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6723203659057617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6329708099365234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5952910780906677},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5494609475135803},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4697663486003876},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.44224974513053894},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2021.emnlp-main.106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.106","pdf_url":"https://aclanthology.org/2021.emnlp-main.106.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.05362","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.05362","pdf_url":"https://arxiv.org/pdf/2110.05362","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.emnlp-main.106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.106","pdf_url":"https://aclanthology.org/2021.emnlp-main.106.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3207482032.pdf","grobid_xml":"https://content.openalex.org/works/W3207482032.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W746041417","https://openalex.org/W1522301498","https://openalex.org/W1555547974","https://openalex.org/W2096335387","https://openalex.org/W2160583993","https://openalex.org/W2167702024","https://openalex.org/W2251552857","https://openalex.org/W2507397568","https://openalex.org/W2593864460","https://openalex.org/W2607050173","https://openalex.org/W2772704197","https://openalex.org/W2952925239","https://openalex.org/W2962691502","https://openalex.org/W2962751953","https://openalex.org/W2963033680","https://openalex.org/W2963087868","https://openalex.org/W2963341956","https://openalex.org/W2964121744","https://openalex.org/W2964151654","https://openalex.org/W2964222246","https://openalex.org/W2965373594","https://openalex.org/W2969574947","https://openalex.org/W2979196189","https://openalex.org/W2987249037","https://openalex.org/W3023491487","https://openalex.org/W3045916626","https://openalex.org/W3089283433","https://openalex.org/W3093830302","https://openalex.org/W3101528337","https://openalex.org/W3104748221","https://openalex.org/W3107441693","https://openalex.org/W3117131443","https://openalex.org/W3119619013","https://openalex.org/W4295312788","https://openalex.org/W4299585995"],"related_works":["https://openalex.org/W2259377089","https://openalex.org/W4281634851","https://openalex.org/W4386566736","https://openalex.org/W3041549465","https://openalex.org/W2380610138","https://openalex.org/W3171444480","https://openalex.org/W4206648670","https://openalex.org/W1495336436","https://openalex.org/W3212412177","https://openalex.org/W3173436410"],"abstract_inverted_index":{"Performing":[0],"event":[1],"and":[2,99,125,138,147],"entity":[3],"coreference":[4,30,50,105,171],"resolution":[5,172],"across":[6,160],"documents":[7],"vastly":[8],"increases":[9],"the":[10,20,72,78,95,100,141],"number":[11],"of":[12,102],"candidate":[13],"mentions,":[14],"making":[15],"it":[16],"intractable":[17],"to":[18,38,55,112,117,168],"do":[19],"full":[21],"$n^2$":[22],"pairwise":[23],"comparisons.":[24],"Existing":[25],"approaches":[26],"simplify":[27],"by":[28,71,163],"considering":[29],"only":[31,114],"within":[32,87],"document":[33],"clusters,":[34],"but":[35],"this":[36],"fails":[37],"handle":[39],"inter-cluster":[40],"coreference,":[41],"common":[42],"in":[43,80,176],"many":[44],"applications.":[45],"As":[46],"a":[47,81,85,88,119,169],"result":[48],"cross-document":[49],"algorithms":[51],"are":[52,69],"rarely":[53],"applied":[54],"downstream":[56,177],"tasks.":[57],"We":[58,76,107],"draw":[59],"on":[60,122,140,154],"an":[61],"insight":[62],"from":[63],"discourse":[64,74,128],"coherence":[65],"theory:":[66],"potential":[67],"coreferences":[68],"constrained":[70],"reader's":[73,82],"focus.":[75],"model":[77,173],"entities/events":[79],"focus":[83],"as":[84],"neighborhood":[86],"learned":[89],"latent":[90],"embedding":[91],"space":[92],"which":[93],"minimizes":[94],"distance":[96],"between":[97],"mentions":[98],"centroids":[101],"their":[103,126],"gold":[104],"clusters.":[106],"then":[108],"use":[109,175],"these":[110],"neighborhoods":[111],"sample":[113],"hard":[115],"negatives":[116],"train":[118],"fine-grained":[120],"classifier":[121],"mention":[123],"pairs":[124],"local":[127],"features.":[129],"Our":[130],"approach":[131],"achieves":[132],"state-of-the-art":[133],"results":[134],"for":[135,174],"both":[136],"events":[137],"entities":[139],"ECB+,":[142],"Gun":[143],"Violence,":[144],"Football":[145],"Coreference,":[146],"Cross-Domain":[148],"Cross-Document":[149],"Coreference":[150],"corpora.":[151],"Furthermore,":[152],"training":[153],"multiple":[155],"corpora":[156],"improves":[157],"average":[158],"performance":[159],"all":[161],"datasets":[162],"17.2":[164],"F1":[165],"points,":[166],"leading":[167],"robust":[170],"tasks":[178],"where":[179],"link":[180],"distribution":[181],"is":[182],"unknown.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}