{"id":"https://openalex.org/W4406458644","doi":"https://doi.org/10.1109/bigdata62323.2024.10825208","title":"Materials-aware Entity Augmentation for Continued Pre-training in Materials Science","display_name":"Materials-aware Entity Augmentation for Continued Pre-training in Materials Science","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458644","doi":"https://doi.org/10.1109/bigdata62323.2024.10825208"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825208","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/A5001679413","display_name":"SangYun Kim","orcid":"https://orcid.org/0000-0002-9101-5704"},"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":"Sangyun 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/A5001679413"],"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":0.23732879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8713","last_page":"8715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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":0.9986000061035156,"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":0.992900013923645,"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/T11719","display_name":"Data Quality and Management","score":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5943514704704285},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.49970483779907227},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06466662883758545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5943514704704285},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.49970483779907227},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06466662883758545},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825208","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/W2963341956","https://openalex.org/W2964864162","https://openalex.org/W2970771982","https://openalex.org/W3034238904","https://openalex.org/W3034949140","https://openalex.org/W3201869313","https://openalex.org/W4225000412","https://openalex.org/W4282935671","https://openalex.org/W4385570852","https://openalex.org/W4389518725","https://openalex.org/W4404783657"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"While":[0],"NLP-based":[1],"approaches":[2],"have":[3],"shown":[4],"promise":[5],"in":[6,60,92],"accelerating":[7],"materials":[8,96],"science":[9],"research,":[10],"scarcity":[11],"of":[12,21,57,74],"training":[13,61],"data":[14,43],"containing":[15],"materials-aware":[16,46,75],"entities":[17,59],"hinders":[18],"the":[19,55,70],"development":[20],"models":[22],"that":[23,40,80],"generalize":[24],"across":[25,87],"domain":[26],"tasks.":[27],"To":[28],"address":[29],"this":[30],"challenge,":[31],"we":[32],"present":[33],"MENTAP,":[34],"a":[35],"novel":[36],"continued":[37,84],"pre-training":[38,85],"framework":[39],"employs":[41],"preliminary":[42],"augmentation":[44],"via":[45],"entity":[47],"extraction":[48],"and":[49,72],"differential":[50],"masking":[51],"strategies.":[52],"By":[53],"improving":[54],"representation":[56],"rare":[58],"data,":[62],"MENTAP":[63,81],"effectively":[64],"mitigates":[65],"long-tail":[66],"distribution":[67],"challenges,":[68],"enhancing":[69],"frequency":[71],"diversity":[73],"entities.":[76],"Comprehensive":[77],"evaluations":[78],"demonstrate":[79],"outperforms":[82],"existing":[83],"methods":[86],"benchmarks,":[88],"underscoring":[89],"its":[90],"effectiveness":[91],"adapting":[93],"PLMs":[94],"to":[95],"science.":[97]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}