{"id":"https://openalex.org/W7126425016","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.128","title":"Jigsaw Pieces of Meaning: Modeling Discourse Coherence with Informed Negative Sample Synthesis","display_name":"Jigsaw Pieces of Meaning: Modeling Discourse Coherence with Informed Negative Sample Synthesis","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126425016","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.128"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.128","pdf_url":"https://aclanthology.org/2024.findings-eacl.128.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.128.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055766947","display_name":"Shubhankar Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shubhankar Singh","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055766947"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59591337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1895","last_page":"1908"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4027000069618225,"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":0.4027000069618225,"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":0.15029999613761902,"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/T12090","display_name":"Language and cultural evolution","score":0.05730000138282776,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"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/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6119999885559082},{"id":"https://openalex.org/keywords/jigsaw","display_name":"Jigsaw","score":0.5691999793052673},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.49970000982284546},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3605000078678131}],"concepts":[{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C2779405079","wikidata":"https://www.wikidata.org/wiki/Q356040","display_name":"Jigsaw","level":2,"score":0.5691999793052673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5526999831199646},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47279998660087585},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3409000039100647},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.24619999527931213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24480000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.128","pdf_url":"https://aclanthology.org/2024.findings-eacl.128.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.128","pdf_url":"https://aclanthology.org/2024.findings-eacl.128.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6617785096168518,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323029","display_name":"Atomic Energy of Canada Limited","ror":"https://ror.org/019ja9e37"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126425016.pdf","grobid_xml":"https://content.openalex.org/works/W7126425016.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Coherence":[0],"in":[1,139],"discourse":[2],"is":[3],"fundamental":[4],"for":[5,59,77,82,92,105,131],"comprehension":[6],"and":[7,19,62,75,101],"perception.Much":[8],"research":[9],"on":[10,15,23,42,109],"coherence":[11,61,94,132],"modeling":[12,95,133],"has":[13],"focused":[14],"better":[16,49,83,135],"model":[17,142],"architectures":[18],"training":[20,90],"setups":[21],"optimizing":[22],"the":[24,118],"permuted":[25],"document":[26,34],"task,":[27],"where":[28],"random":[29],"permutations":[30],"of":[31,85,112,120],"a":[32,55,88,110,127],"coherent":[33],"are":[35],"considered":[36],"incoherent.However,":[37],"there's":[38],"very":[39],"limited":[40],"work":[41],"creating":[43],"\"informed\"":[44,78],"synthetic":[45],"incoherent":[46],"samples":[47],"that":[48,126],"represent":[50],"or":[51],"mimic":[52],"incoherence.We":[53,86],"source":[54],"diverse":[56],"positive":[57],"corpus":[58],"local":[60,93,103],"propose":[63],"six":[64],"rule-based":[65],"methods":[66],"leveraging":[67],"information":[68],"from":[69],"Constituency":[70],"trees,":[71],"Part-of-speech,":[72],"semantic":[73],"overlap":[74],"more,":[76],"negative":[79,122,136],"sample":[80,123,137],"synthesis":[81,138],"representation":[84],"keep":[87],"straightforward":[89],"setup":[91],"by":[96],"fine-tuning":[97],"popular":[98],"transformer":[99],"models,":[100],"aggregate":[102],"scores":[104],"global":[106],"coherence.We":[107],"evaluate":[108],"battery":[111],"independent":[113],"downstream":[114],"tasks":[115],"to":[116],"assess":[117],"impact":[119],"improved":[121],"quality.We":[124],"assert":[125],"step":[128],"towards":[129],"optimality":[130],"requires":[134],"tandem":[140],"with":[141],"improvements.":[143]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2026-02-02T00:00:00"}