{"id":"https://openalex.org/W4412945548","doi":"https://doi.org/10.18653/v1/2025.acl-long.474","title":"Incorporating Domain Knowledge into Materials Tokenization","display_name":"Incorporating Domain Knowledge into Materials Tokenization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945548","doi":"https://doi.org/10.18653/v1/2025.acl-long.474"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.474","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.474","pdf_url":"https://aclanthology.org/2025.acl-long.474.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.474.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114534299","display_name":"Yerim Oh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yerim Oh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787663","display_name":"Jun-Hyung Park","orcid":"https://orcid.org/0000-0002-7900-3743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun-Hyung Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050925695","display_name":"Junho Kim","orcid":"https://orcid.org/0000-0002-5947-2147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junho Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619135","display_name":"Sungho Kim","orcid":"https://orcid.org/0000-0002-7004-3482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"SungHo Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112456750","display_name":"SangKeun Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"SangKeun Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24451853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9623","last_page":"9644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10783","display_name":"Additive Manufacturing and 3D Printing Technologies","score":0.9348999857902527,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12080","display_name":"Injection Molding Process and Properties","score":0.9088000059127808,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.7440692782402039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7268459796905518},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5403016805648804},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35493969917297363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32606205344200134},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06154218316078186}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7440692782402039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268459796905518},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5403016805648804},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35493969917297363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32606205344200134},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06154218316078186},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.474","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.474","pdf_url":"https://aclanthology.org/2025.acl-long.474.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.474","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.474","pdf_url":"https://aclanthology.org/2025.acl-long.474.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8458676037","display_name":null,"funder_award_id":"RS-2019-II190079","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8566920739","display_name":null,"funder_award_id":"RS-2024-00415812","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G960095468","display_name":null,"funder_award_id":"RS-2019-II190079","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945548.pdf","grobid_xml":"https://content.openalex.org/works/W4412945548.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4405003489","https://openalex.org/W4300598845","https://openalex.org/W3204019825","https://openalex.org/W2601638452","https://openalex.org/W2285263069","https://openalex.org/W4376107815","https://openalex.org/W4319309671"],"abstract_inverted_index":{"While":[0],"language":[1,20],"models":[2,10],"are":[3],"increasingly":[4],"utilized":[5],"in":[6,73,114,131],"materials":[7,63],"science,":[8],"typical":[9],"rely":[11],"on":[12,58,61],"frequency-centric":[13],"tokenization":[14,50,103,129],"methods":[15,23],"originally":[16],"developed":[17],"for":[18,128],"natural":[19],"processing.However,":[21],"these":[22],"frequently":[24],"produce":[25],"excessive":[26],"fragmentation":[27,87],"and":[28,36,66,85,112,117],"semantic":[29,37,92],"loss,":[30],"failing":[31],"to":[32],"maintain":[33],"the":[34,78,115,123],"structural":[35,79],"integrity":[38,80],"of":[39,81,110,125],"material":[40,54,71,83],"concepts.To":[41],"address":[42],"this":[43],"issue,":[44],"we":[45],"propose":[46],"MATTER,":[47],"a":[48,67],"novel":[49],"approach":[51],"that":[52,99],"integrates":[53],"knowledge":[55,64,127],"into":[56],"tokenization.Based":[57],"MatDetector":[59],"trained":[60],"our":[62],"base":[65],"re-ranking":[68],"method":[69],"prioritizing":[70],"concepts":[72,84],"token":[74],"merging,":[75],"MATTER":[76,100],"maintains":[77],"identified":[82],"prevents":[86],"during":[88],"tokenization,":[89],"ensuring":[90],"their":[91],"meaning":[93],"remains":[94],"intact.The":[95],"experimental":[96],"results":[97,121],"demonstrate":[98],"outperforms":[101],"existing":[102],"methods,":[104],"achieving":[105],"an":[106],"average":[107],"performance":[108],"gain":[109],"4%":[111],"2%":[113],"generation":[116],"classification":[118],"tasks,":[119],"respectively.These":[120],"underscore":[122],"importance":[124],"domain":[126],"strategies":[130],"scientific":[132],"text":[133],"processing.":[134],"1":[135]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}