{"id":"https://openalex.org/W2807505183","doi":"https://doi.org/10.18653/v1/w18-1703","title":"Multi-hop Inference for Sentence-level TextGraphs: How Challenging is Meaningfully Combining Information for Science Question Answering?","display_name":"Multi-hop Inference for Sentence-level TextGraphs: How Challenging is Meaningfully Combining Information for Science Question Answering?","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2807505183","doi":"https://doi.org/10.18653/v1/w18-1703","mag":"2807505183"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-1703","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-1703","pdf_url":"https://www.aclweb.org/anthology/W18-1703.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 Twelfth Workshop on Graph-Based Methods for Natural\n          Language Processing (TextGraphs-12)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-1703.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111404777","display_name":"Peter Jansen","orcid":null},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]},{"id":"https://openalex.org/I2801768934","display_name":"Defense Information School","ror":"https://ror.org/04t5yz624","country_code":"US","type":"education","lineage":["https://openalex.org/I1330347796","https://openalex.org/I2801768934"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peter Jansen","raw_affiliation_strings":["School of Information, University of Arizona, Tucson, AZ","Information, School of"],"affiliations":[{"raw_affiliation_string":"School of Information, University of Arizona, Tucson, AZ","institution_ids":["https://openalex.org/I138006243"]},{"raw_affiliation_string":"Information, School of","institution_ids":["https://openalex.org/I2801768934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5111404777"],"corresponding_institution_ids":["https://openalex.org/I138006243","https://openalex.org/I2801768934"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06066328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9923999905586243,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9918000102043152,"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/inference","display_name":"Inference","score":0.7651004195213318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7591673135757446},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.7407961487770081},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.670623242855072},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5709143280982971},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.5402460098266602},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5093611478805542},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5053775906562805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4676990509033203},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.42971330881118774},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41840702295303345},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41068220138549805},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2696596384048462},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2533685564994812},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16205239295959473}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7651004195213318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591673135757446},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.7407961487770081},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.670623242855072},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5709143280982971},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.5402460098266602},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5093611478805542},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5053775906562805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4676990509033203},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.42971330881118774},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41840702295303345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41068220138549805},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2696596384048462},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2533685564994812},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16205239295959473},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w18-1703","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-1703","pdf_url":"https://www.aclweb.org/anthology/W18-1703.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 Twelfth Workshop on Graph-Based Methods for Natural\n          Language Processing (TextGraphs-12)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.11267","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.11267","pdf_url":"https://arxiv.org/pdf/1805.11267","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1805.11267","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.11267","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:2807505183","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/w18-1703","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-1703","pdf_url":"https://www.aclweb.org/anthology/W18-1703.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 Twelfth Workshop on Graph-Based Methods for Natural\n          Language Processing (TextGraphs-12)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8600000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2807505183.pdf","grobid_xml":"https://content.openalex.org/works/W2807505183.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1997897354","https://openalex.org/W2024650720","https://openalex.org/W2112706073","https://openalex.org/W2125444198","https://openalex.org/W2337282450","https://openalex.org/W2512994153","https://openalex.org/W2575101981","https://openalex.org/W2608309533","https://openalex.org/W2765383698","https://openalex.org/W2786395785","https://openalex.org/W2790767126"],"related_works":["https://openalex.org/W2963339923","https://openalex.org/W2988558230","https://openalex.org/W3031043369","https://openalex.org/W2962999949","https://openalex.org/W2979196189","https://openalex.org/W3186065854","https://openalex.org/W3125115207","https://openalex.org/W1591825359","https://openalex.org/W2126034021","https://openalex.org/W2999215229","https://openalex.org/W2970647290","https://openalex.org/W2963714798","https://openalex.org/W3081814550","https://openalex.org/W2517782820","https://openalex.org/W2991372099","https://openalex.org/W3200460059","https://openalex.org/W3035168168","https://openalex.org/W3091091747","https://openalex.org/W2110827010","https://openalex.org/W2761886726"],"abstract_inverted_index":{"Question":[0],"Answering":[1],"for":[2,62],"complex":[3],"questions":[4,85],"is":[5,73],"often":[6],"modelled":[7],"as":[8,81],"a":[9,16,22,30,74,110],"graph":[10,23,111],"construction":[11],"or":[12,20,59,108],"traversal":[13],"task,":[14],"where":[15],"solver":[17],"must":[18],"build":[19],"traverse":[21],"of":[24,65,89,106,112,166],"facts":[25,52,66,93],"that":[26,162],"answer":[27,95],"and":[28,96,139,150,157,159],"explain":[29],"given":[31],"question.":[32],"This":[33,72],"\"multi-hop\"":[34],"inference":[35,79],"has":[36],"been":[37],"shown":[38],"to":[39,47,67,77,91,94,147],"be":[40,148],"extremely":[41],"challenging,":[42],"with":[43],"few":[44],"models":[45],"able":[46],"aggregate":[48],"more":[49],"than":[50],"two":[51],"before":[53],"being":[54],"overwhelmed":[55],"by":[56,115,118],"\"semantic":[57],"drift\",":[58],"the":[60,104,164],"tendency":[61],"long":[63],"chains":[64],"quickly":[68],"drift":[69,145],"off":[70],"topic.":[71],"major":[75],"barrier":[76],"current":[78],"models,":[80],"even":[82],"elementary":[83],"science":[84],"require":[86],"an":[87],"average":[88],"4":[90],"6":[92],"explain.":[97],"In":[98],"this":[99],"work":[100],"we":[101],"empirically":[102],"characterize":[103],"difficulty":[105],"building":[107],"traversing":[109],"sentences":[113],"connected":[114],"lexical":[116],"overlap,":[117],"evaluating":[119],"chance":[120],"sentence":[121],"aggregation":[122,151],"quality":[123,152],"through":[124],"9,784":[125],"manually-annotated":[126],"judgements":[127],"across":[128],"knowledge":[129],"graphs":[130],"built":[131],"from":[132],"three":[133],"freetext":[134],"corpora":[135],"(including":[136],"study":[137],"guides":[138],"Simple":[140],"Wikipedia).":[141],"We":[142],"demonstrate":[143],"semantic":[144],"tends":[146],"high":[149],"low,":[153],"at":[154],"between":[155],"0.04%":[156],"3%,":[158],"highlight":[160],"scenarios":[161],"maximize":[163],"likelihood":[165],"meaningfully":[167],"combining":[168],"information.":[169]},"counts_by_year":[],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-10-04T00:00:00"}