{"id":"https://openalex.org/W4399357168","doi":"https://doi.org/10.48550/arxiv.2406.00562","title":"SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing","display_name":"SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing","publication_year":2024,"publication_date":"2024-06-01","ids":{"openalex":"https://openalex.org/W4399357168","doi":"https://doi.org/10.48550/arxiv.2406.00562"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.00562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.00562","pdf_url":"https://arxiv.org/pdf/2406.00562","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.00562","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107242554","display_name":"Heidi C. Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Heidi C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031309131","display_name":"Sina J. Semnani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Semnani, Sina J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087852808","display_name":"Farhad Ghassemi","orcid":"https://orcid.org/0009-0003-2825-1979"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghassemi, Farhad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023143758","display_name":"Jialiang Xu","orcid":"https://orcid.org/0000-0003-2441-4809"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jialiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018640318","display_name":"Shicheng Liu","orcid":"https://orcid.org/0000-0002-0843-284X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002419188","display_name":"Monica S. Lam","orcid":"https://orcid.org/0000-0002-1205-1302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lam, Monica S.","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":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9871000051498413,"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":0.9871000051498413,"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":0.9675999879837036,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9437000155448914,"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/parsing","display_name":"Parsing","score":0.7634681463241577},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7568385601043701},{"id":"https://openalex.org/keywords/open-domain","display_name":"Open domain","score":0.7261635661125183},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7250338196754456},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6105248928070068},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.568106472492218},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41312935948371887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3506867289543152},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09007036685943604}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7634681463241577},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7568385601043701},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.7261635661125183},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250338196754456},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6105248928070068},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.568106472492218},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41312935948371887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3506867289543152},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09007036685943604},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.00562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.00562","pdf_url":"https://arxiv.org/pdf/2406.00562","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.00562","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.00562","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.00562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.00562","pdf_url":"https://arxiv.org/pdf/2406.00562","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399357168.pdf","grobid_xml":"https://content.openalex.org/works/W4399357168.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2391533720","https://openalex.org/W2951097643","https://openalex.org/W4309395021","https://openalex.org/W3215363805","https://openalex.org/W204133468","https://openalex.org/W2991310128","https://openalex.org/W4307481286","https://openalex.org/W6643695","https://openalex.org/W2395174199","https://openalex.org/W4226441484"],"abstract_inverted_index":{"We":[0],"introduce":[1],"SPAGHETTI:":[2],"Semantic":[3],"Parsing":[4],"Augmented":[5],"Generation":[6],"for":[7,83],"Hybrid":[8],"English":[9],"information":[10,23],"from":[11,24],"Text":[12],"Tables":[13],"and":[14,33],"Infoboxes,":[15],"a":[16,63],"hybrid":[17],"question-answering":[18],"(QA)":[19],"pipeline":[20],"that":[21,69,77],"utilizes":[22],"heterogeneous":[25,48],"knowledge":[26,29],"sources,":[27],"including":[28],"base,":[30],"text,":[31],"tables,":[32],"infoboxes.":[34],"Our":[35],"LLM-augmented":[36],"approach":[37],"achieves":[38],"state-of-the-art":[39],"performance":[40],"on":[41,62],"the":[42,45,66,85],"Compmix":[43],"dataset,":[44,51],"most":[46],"comprehensive":[47],"open-domain":[49],"QA":[50,88],"with":[52],"56.5%":[53],"exact":[54],"match":[55],"(EM)":[56],"rate.":[57],"More":[58],"importantly,":[59],"manual":[60],"analysis":[61],"sample":[64],"of":[65,87],"dataset":[67],"suggests":[68],"SPAGHETTI":[70],"is":[71,79],"more":[72],"than":[73],"90%":[74],"accurate,":[75],"indicating":[76],"EM":[78],"no":[80],"longer":[81],"suitable":[82],"assessing":[84],"capabilities":[86],"systems":[89],"today.":[90]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2024-06-06T00:00:00"}