{"id":"https://openalex.org/W4412887811","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1146","title":"Unsupervised Morphological Tree Tokenizer","display_name":"Unsupervised Morphological Tree Tokenizer","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887811","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1146"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1146","pdf_url":"https://aclanthology.org/2025.findings-acl.1146.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: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1146.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101493235","display_name":"Qingyang Zhu","orcid":"https://orcid.org/0000-0001-7205-5199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyang Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100606894","display_name":"Xiang Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111237864","display_name":"Pengyu Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengyu Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079315017","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0002-4476-7639"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102274699","display_name":"Kewei Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kewei Tu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.14213124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22299","last_page":"22312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.555899977684021,"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/T10320","display_name":"Neural Networks and Applications","score":0.555899977684021,"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/computer-science","display_name":"Computer science","score":0.6475033164024353},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6225373148918152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47760865092277527},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3885301351547241},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08541983366012573},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07447347044944763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6475033164024353},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6225373148918152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47760865092277527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3885301351547241},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08541983366012573},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07447347044944763}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1146","pdf_url":"https://aclanthology.org/2025.findings-acl.1146.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1146","pdf_url":"https://aclanthology.org/2025.findings-acl.1146.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5693414920","display_name":"NRT-HDR: FUTURE Foundations, Translation, and Responsibility for Data Science Impact","funder_award_id":"1922658","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887811.pdf","grobid_xml":"https://content.openalex.org/works/W4412887811.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/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"As":[0],"a":[1,39,60,105],"cornerstone":[2],"in":[3,104],"language":[4,134],"modeling,":[5],"tokenization":[6,36],"involves":[7],"segmenting":[8],"text":[9],"inputs":[10],"into":[11],"pre-defined":[12],"atomic":[13],"units.Conventional":[14],"statistical":[15],"tokenizers":[16],"often":[17],"disrupt":[18],"constituent":[19],"boundaries":[20],"within":[21],"words,":[22],"thereby":[23],"corrupting":[24],"semantic":[25],"information.To":[26],"address":[27],"this":[28],"drawback,":[29],"we":[30],"introduce":[31],"morphological":[32,87,130],"structure":[33],"guidance":[34],"to":[35,42,64],"and":[37,55,118,126,133],"propose":[38],"deep":[40,49],"model":[41,50,72],"induce":[43],"character-level":[44],"structures":[45,54,83],"of":[46,57,68,80],"words.Specifically,":[47],"the":[48,66,71,94,111],"jointly":[51],"encodes":[52],"internal":[53],"representations":[56],"words":[58,100],"with":[59,73,86],"mechanism":[61],"named":[62],"MorphOverriding":[63],"ensure":[65],"indecomposability":[67],"morphemes.By":[69],"training":[70,91],"self-supervised":[74],"objectives,":[75],"our":[76,97],"method":[77,113],"is":[78],"capable":[79],"inducing":[81],"characterlevel":[82],"that":[84,110],"align":[85],"rules":[88],"without":[89],"annotated":[90],"data.Based":[92],"on":[93,128],"induced":[95],"structures,":[96],"algorithm":[98],"tokenizes":[99],"through":[101],"vocabulary":[102],"matching":[103],"top-down":[106],"manner.Empirical":[107],"results":[108],"indicate":[109],"proposed":[112],"effectively":[114],"retains":[115],"complete":[116],"morphemes":[117],"outperforms":[119],"widely":[120],"adopted":[121],"methods":[122],"such":[123],"as":[124],"BPE":[125],"WordPiece":[127],"both":[129],"segmentation":[131],"tasks":[132],"modeling":[135],"tasks.":[136]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}