{"id":"https://openalex.org/W4402787020","doi":"https://doi.org/10.1515/itit-2023-0065","title":"Towards a word similarity gold standard for Akkadian: creation and model optimization","display_name":"Towards a word similarity gold standard for Akkadian: creation and model optimization","publication_year":2024,"publication_date":"2024-02-01","ids":{"openalex":"https://openalex.org/W4402787020","doi":"https://doi.org/10.1515/itit-2023-0065"},"language":"en","primary_location":{"id":"doi:10.1515/itit-2023-0065","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1515/itit-2023-0065","pdf_url":null,"source":{"id":"https://openalex.org/S4210229153","display_name":"it - Information Technology","issn_l":"1611-2776","issn":["1611-2776","2196-7032"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319967","host_organization_name":"R. Oldenbourg Verlag","host_organization_lineage":["https://openalex.org/P4310319967"],"host_organization_lineage_names":["R. Oldenbourg Verlag"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"it - Information Technology","raw_type":"journal-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/A5015516895","display_name":"Aleksi Sahala","orcid":"https://orcid.org/0000-0002-4255-3872"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Aleksi Sahala","raw_affiliation_strings":["Digital Humanities , University of Helsinki , Helsinki , Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Humanities , University of Helsinki , Helsinki , Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059694008","display_name":"Beatrice Baragli","orcid":"https://orcid.org/0000-0002-3549-2012"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Beatrice Baragli","raw_affiliation_strings":["Ancient Near Eastern Studies , University of W\u00fcrzburg , W\u00fcrzburg , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ancient Near Eastern Studies , University of W\u00fcrzburg , W\u00fcrzburg , Germany","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107575607","display_name":"Giulia Lentini","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Giulia Lentini","raw_affiliation_strings":["Ancient History , LMU Munich , Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ancient History , LMU Munich , Munich , Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024458238","display_name":"Poppy Tushingham","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Poppy Tushingham","raw_affiliation_strings":["Ancient History , LMU Munich , Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ancient History , LMU Munich , Munich , Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13403749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"66","issue":"1","first_page":"4","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9954000115394592,"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/akkadian","display_name":"Akkadian","score":0.8132562041282654},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6444604396820068},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6178197860717773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5051754117012024},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.48766982555389404},{"id":"https://openalex.org/keywords/gold-standard","display_name":"Gold standard (test)","score":0.47145137190818787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4629754424095154},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.35665804147720337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35651451349258423},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24406903982162476},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16350987553596497},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.15453875064849854}],"concepts":[{"id":"https://openalex.org/C2781354927","wikidata":"https://www.wikidata.org/wiki/Q35518","display_name":"Akkadian","level":2,"score":0.8132562041282654},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6444604396820068},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6178197860717773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5051754117012024},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.48766982555389404},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.47145137190818787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4629754424095154},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.35665804147720337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35651451349258423},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24406903982162476},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16350987553596497},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.15453875064849854},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1515/itit-2023-0065","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1515/itit-2023-0065","pdf_url":null,"source":{"id":"https://openalex.org/S4210229153","display_name":"it - Information Technology","issn_l":"1611-2776","issn":["1611-2776","2196-7032"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319967","host_organization_name":"R. Oldenbourg Verlag","host_organization_lineage":["https://openalex.org/P4310319967"],"host_organization_lineage_names":["R. Oldenbourg Verlag"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"it - Information Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W1593045043","https://openalex.org/W1614298861","https://openalex.org/W1615991656","https://openalex.org/W1662133657","https://openalex.org/W1854884267","https://openalex.org/W2067438047","https://openalex.org/W2080100102","https://openalex.org/W2112184938","https://openalex.org/W2125031621","https://openalex.org/W2250539671","https://openalex.org/W2482825055","https://openalex.org/W2493916176","https://openalex.org/W2803437449","https://openalex.org/W3029601947","https://openalex.org/W3101979452"],"related_works":["https://openalex.org/W2019227522","https://openalex.org/W2320328184","https://openalex.org/W4310204390","https://openalex.org/W2737697110","https://openalex.org/W3162048390","https://openalex.org/W2241678908","https://openalex.org/W2527112146","https://openalex.org/W3010961981","https://openalex.org/W2992919036","https://openalex.org/W2296205523"],"abstract_inverted_index":{"Abstract":[0],"We":[1,44,61],"present":[2,63],"a":[3,10,64],"word":[4,32,73],"similarity":[5,38,102],"gold":[6,28,47],"standard":[7,29,48],"for":[8,70],"Akkadian,":[9],"language":[11],"documented":[12],"in":[13,87],"ancient":[14],"Mesopotamian":[15],"sources":[16],"from":[17],"the":[18,23,46,80],"24th":[19],"century":[20,25],"BCE":[21],"until":[22],"first":[24],"CE.":[26],"The":[27],"comprises":[30],"300":[31],"pairs":[33],"ranked":[34],"by":[35,39,108],"their":[36,59],"paradigmatic":[37],"five":[40],"independently":[41],"working":[42],"Assyriologists.":[43],"use":[45],"to":[49,57,77,104],"tune":[50],"PMI":[51,66],"+":[52,67],"SVD":[53,68],"and":[54,83,99,111],"fastText":[55],"models":[56],"improve":[58],"performance.":[60],"also":[62],"hyper-parametrized":[65],"model":[69,91],"building":[71],"count-based":[72],"embeddings,":[74],"that":[75],"aims":[76],"deal":[78],"with":[79,95],"data":[81],"sparsity":[82],"repetition":[84],"issues":[85],"encountered":[86],"Akkadian":[88],"texts.":[89],"Our":[90],"combines":[92],"Dirichlet":[93],"smoothing":[94],"context":[96,101],"distribution":[97],"smoothing,":[98],"uses":[100],"weighting":[103],"down-sample":[105],"distortion":[106],"caused":[107],"formulaic":[109],"litanies":[110],"partially":[112],"or":[113],"fully":[114],"duplicated":[115],"passages.":[116]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
