{"id":"https://openalex.org/W4406457844","doi":"https://doi.org/10.1109/bigdata62323.2024.10825965","title":"Embedding-based Entity Expansion for Data Augmentation in Materials Science","display_name":"Embedding-based Entity Expansion for Data Augmentation in Materials Science","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406457844","doi":"https://doi.org/10.1109/bigdata62323.2024.10825965"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","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/A5101761898","display_name":"Suho Kim","orcid":"https://orcid.org/0000-0001-8668-5036"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Suho Kim","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101761898"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32045966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8710","last_page":"8712"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"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":0.9872999787330627,"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/embedding","display_name":"Embedding","score":0.7203472852706909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6906521916389465},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.369972825050354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36356037855148315},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33189475536346436}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7203472852706909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6906521916389465},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.369972825050354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36356037855148315},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33189475536346436}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2523785361","https://openalex.org/W2953641512","https://openalex.org/W2963341956","https://openalex.org/W2964864162","https://openalex.org/W3034949140","https://openalex.org/W3201869313","https://openalex.org/W4224442790","https://openalex.org/W4285106586","https://openalex.org/W4288089799","https://openalex.org/W4385571216","https://openalex.org/W4404781281","https://openalex.org/W6769627184"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2932872266"],"abstract_inverted_index":{"NLP-based":[0],"techniques":[1],"have":[2],"demonstrated":[3],"notable":[4],"success":[5],"in":[6,83,126],"tasks":[7],"like":[8],"entity":[9,77],"recognition":[10],"within":[11],"materials":[12,85,120],"science":[13,86,121],"[1]":[14],"[2].":[15],"However,":[16],"the":[17,25,42,62,84,101],"field":[18],"suffers":[19],"from":[20,93],"data":[21,37,81,128],"scarcity":[22],"due":[23],"to":[24,99],"resource-intensive":[26],"nature":[27],"of":[28,41,103],"generating":[29],"high-quality":[30],"annotated":[31],"data.":[32],"To":[33,69],"address":[34,70],"this":[35],"issue,":[36],"augmentation":[38,82],"is":[39],"one":[40],"promising":[43],"approaches.":[44],"Yet,":[45],"prior":[46],"studies":[47],"[3]":[48],"[4]":[49],"primarily":[50],"transform":[51],"human-annotated":[52],"entities,":[53],"which":[54],"are":[55],"often":[56],"noisy":[57],"and":[58,96],"incomplete,":[59],"potentially":[60],"limiting":[61],"diversity":[63],"needed":[64],"for":[65,80],"robust":[66],"model":[67],"development.":[68],"this,":[71],"we":[72],"propose":[73],"EXPAND,":[74],"an":[75],"embedding-based":[76],"expansion":[78],"framework":[79],"domain.":[87],"EXPAND":[88],"leverages":[89],"materials-aware":[90],"embeddings":[91],"derived":[92],"ChemDataExtractor":[94],"[5]":[95],"Mat2Vec":[97],"[6]":[98],"expand":[100],"range":[102],"entities":[104],"beyond":[105],"human":[106],"annotations.":[107],"Our":[108],"proposed":[109],"method":[110],"achieves":[111],"a":[112],"1.5%":[113],"improvement":[114],"over":[115],"baseline":[116],"methods":[117],"across":[118],"various":[119],"benchmarks,":[122],"demonstrating":[123],"its":[124],"effectiveness":[125],"overcoming":[127],"scarcity.":[129]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}