{"id":"https://openalex.org/W7064078568","doi":null,"title":"AstroDB Data Extraction: A Comparative Analysis of Embedding, Query Expansion, and Filtering Techniques","display_name":"AstroDB Data Extraction: A Comparative Analysis of Embedding, Query Expansion, and Filtering Techniques","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7064078568"},"language":"en","primary_location":{"id":"pmh:oai:repository.arizona.edu:10150/677953","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10150/677953","pdf_url":"https://repository.arizona.edu/bitstream/10150/677953/1/azu_etd_22171_sip1_m.pdf","source":{"id":"https://openalex.org/S4306400271","display_name":"UA Campus Repository (The University of Arizona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I138006243","host_organization_name":"University of Arizona","host_organization_lineage":["https://openalex.org/I138006243"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Electronic Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.arizona.edu/bitstream/10150/677953/1/azu_etd_22171_sip1_m.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Feng, Baoying","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Baoying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Feng, Baoying","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Baoying","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4242999851703644,"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":0.4242999851703644,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.20919999480247498,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.04309999942779541,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/embeddings","display_name":"embeddings","score":0.6069999933242798},{"id":"https://openalex.org/keywords/query-expansion","display_name":"query expansion","score":0.9990000128746033},{"id":"https://openalex.org/keywords/filtering-techniques","display_name":"filtering techniques","score":0.8330000042915344},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.921999990940094},{"id":"https://openalex.org/keywords/scientific-publications","display_name":"scientific publications","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7889000177383423},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7037000060081482},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5529999732971191},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.3393000066280365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30799999833106995},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3009999990463257},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2662000060081482}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:repository.arizona.edu:10150/677953","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10150/677953","pdf_url":"https://repository.arizona.edu/bitstream/10150/677953/1/azu_etd_22171_sip1_m.pdf","source":{"id":"https://openalex.org/S4306400271","display_name":"UA Campus Repository (The University of Arizona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I138006243","host_organization_name":"University of Arizona","host_organization_lineage":["https://openalex.org/I138006243"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Electronic Thesis"}],"best_oa_location":{"id":"pmh:oai:repository.arizona.edu:10150/677953","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10150/677953","pdf_url":"https://repository.arizona.edu/bitstream/10150/677953/1/azu_etd_22171_sip1_m.pdf","source":{"id":"https://openalex.org/S4306400271","display_name":"UA Campus Repository (The University of Arizona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I138006243","host_organization_name":"University of Arizona","host_organization_lineage":["https://openalex.org/I138006243"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Electronic Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7064078568.pdf","grobid_xml":"https://content.openalex.org/works/W7064078568.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2978017171","https://openalex.org/W3007672467","https://openalex.org/W3027879771","https://openalex.org/W3034439313","https://openalex.org/W4375870261","https://openalex.org/W4378469337","https://openalex.org/W4385681528","https://openalex.org/W4389519226","https://openalex.org/W4404239715","https://openalex.org/W4405029855","https://openalex.org/W4405562150","https://openalex.org/W4408354806","https://openalex.org/W4414014501"],"related_works":["https://openalex.org/W4392669797","https://openalex.org/W2803171807","https://openalex.org/W4416354549","https://openalex.org/W3217652161","https://openalex.org/W4394673924","https://openalex.org/W1631200718","https://openalex.org/W4412443110","https://openalex.org/W7114947856","https://openalex.org/W7153300043","https://openalex.org/W4404902168"],"abstract_inverted_index":{"Due":[0],"to":[1,12,27,36,73,86],"the":[2,18,38,48,53,88],"rapid":[3],"growth":[4],"of":[5,43,63],"astrophysical":[6],"scientific":[7,19,94],"papers,":[8],"it":[9],"is":[10],"difficult":[11],"extract":[13],"important":[14],"data":[15,50,89],"manually":[16],"from":[17],"papers.":[20],"While":[21],"traditional":[22],"search":[23],"engines":[24],"can":[25],"help":[26],"find":[28],"relevant":[29],"publications,":[30],"they":[31],"may":[32],"not":[33],"be":[34],"able":[35],"capture":[37],"numerical":[39],"and":[40,60,92],"contextual":[41],"details":[42],"significance.":[44],"This":[45],"thesis":[46],"explores":[47],"multi-modal":[49],"extraction":[51,66,90],"in":[52,70,96],"AstroDB.":[54],"The":[55],"accuracy,":[56],"LLM":[57],"token":[58],"usage,":[59],"run":[61],"time":[62],"various":[64],"combination":[65],"methodologies":[67],"are":[68],"compared":[69],"this":[71],"study":[72],"reveal":[74],"key":[75],"precision":[76],"versus":[77],"computational":[78],"efficiency":[79],"trade-offs.":[80],"These":[81],"insights":[82],"provide":[83],"a":[84],"way":[85],"improve":[87],"pipeline":[91],"accelerate":[93],"discovery":[95],"astrophysics.":[97]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}