{"id":"https://openalex.org/W7126463335","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.66","title":"Learning High-Quality and General-Purpose Phrase Representations","display_name":"Learning High-Quality and General-Purpose Phrase Representations","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126463335","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.66"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.66","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.66","pdf_url":"https://aclanthology.org/2024.findings-eacl.66.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.66.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lihu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lihu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gael Varoquaux","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gael Varoquaux","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Fabian Suchanek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabian Suchanek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3005,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70075301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"983","last_page":"994"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.580299973487854,"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":0.580299973487854,"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/T10028","display_name":"Topic Modeling","score":0.06019999831914902,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.044199999421834946,"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/phrase","display_name":"Phrase","score":0.5304999947547913},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.34450000524520874},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3353999853134155},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.2969000041484833},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.296099990606308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5543000102043152},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5196999907493591},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.51419997215271},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4569000005722046},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.34450000524520874},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.2969000041484833},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26499998569488525}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.66","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.66","pdf_url":"https://aclanthology.org/2024.findings-eacl.66.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.66","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.66","pdf_url":"https://aclanthology.org/2024.findings-eacl.66.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":[{"id":"https://metadata.un.org/sdg/4","score":0.4583238661289215,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1787181088","display_name":"Learning data integration, from discrete entities to signals","funder_award_id":"ANR-20-CHIA-0026","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8442890028","display_name":"Modeling and Extracting Complex Information from Natural Language Text","funder_award_id":"ANR-20-CHIA-0012","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126463335.pdf","grobid_xml":"https://content.openalex.org/works/W7126463335.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Phrase":[0],"representations":[1,73,89],"play":[2],"an":[3,83,100],"important":[4],"role":[5],"in":[6,90],"data":[7,118],"science":[8],"and":[9,23,54,69,79,103],"natural":[10],"language":[11,32],"processing,":[12],"benefiting":[13],"various":[14],"tasks":[15,133],"like":[16],"Entity":[17],"Alignment,":[18],"Record":[19],"Linkage,":[20],"Fuzzy":[21],"Joins,":[22],"Paraphrase":[24],"Classification.The":[25],"current":[26],"state-of-theart":[27],"method":[28],"involves":[29],"fine-tuning":[30],"pre-trained":[31,58],"models":[33,48],"for":[34,44],"phrasal":[35],"embeddings":[36,141],"using":[37],"contrastive":[38],"learning.However,":[39],"we":[40,113],"have":[41],"identified":[42],"areas":[43],"improvement.First,":[45],"these":[46],"pretrained":[47],"tend":[49],"to":[50,56,86,120,143],"be":[51,57],"unnecessarily":[52],"complex":[53],"require":[55],"on":[59],"a":[60,91,129,148],"corpus":[61],"with":[62],"context":[63],"sentences.Second,":[64],"leveraging":[65],"the":[66,110,122],"phrase":[67,72,88,96,111,140],"type":[68,97],"morphology":[70],"gives":[71],"that":[74,135],"are":[75],"both":[76],"more":[77,80,107],"precise":[78],"flexible.We":[81],"propose":[82],"improved":[84],"framework":[85,94],"learn":[87],"context-free":[92],"fashion.The":[93],"employs":[95],"classification":[98],"as":[99],"auxiliary":[101],"task":[102],"incorporates":[104],"character-level":[105],"information":[106],"effectively":[108],"into":[109],"representation.Furthermore,":[112],"design":[114],"three":[115],"granularities":[116],"of":[117,124,132],"augmentation":[119],"increase":[121],"diversity":[123],"training":[125],"samples.Our":[126],"experiments":[127],"across":[128],"wide":[130],"range":[131],"show":[134],"our":[136],"approach":[137],"generates":[138],"superior":[139],"compared":[142],"previous":[144],"methods":[145],"while":[146],"requiring":[147],"smaller":[149],"model":[150],"size.The":[151],"code":[152],"is":[153],"available":[154],"at":[155],"https:":[156],"//github.com/tigerchen52/PEARL":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}