{"id":"https://openalex.org/W2798639660","doi":"https://doi.org/10.1145/3209978.3210174","title":"Combining Terrier with Apache Spark to create Agile Experimental Information Retrieval Pipelines","display_name":"Combining Terrier with Apache Spark to create Agile Experimental Information Retrieval Pipelines","publication_year":2018,"publication_date":"2018-06-27","ids":{"openalex":"https://openalex.org/W2798639660","doi":"https://doi.org/10.1145/3209978.3210174","mag":"2798639660"},"language":"en","primary_location":{"id":"doi:10.1145/3209978.3210174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209978.3210174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057643560","display_name":"Craig Macdonald","orcid":"https://orcid.org/0000-0003-3143-279X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Craig Macdonald","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5057643560"],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":2.0472,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.89844212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1309","last_page":"1312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8529000282287598,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8529000282287598,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.7736999988555908,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.7731000185012817,"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/spark","display_name":"SPARK (programming language)","score":0.8077836632728577},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.6634713411331177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6541624069213867},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5081136226654053},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3227056562900543},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1987454891204834},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.16725242137908936},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.08788031339645386},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07723510265350342}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8077836632728577},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.6634713411331177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6541624069213867},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5081136226654053},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3227056562900543},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1987454891204834},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.16725242137908936},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.08788031339645386},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07723510265350342}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3209978.3210174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209978.3210174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:160904","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:160904","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2588670714"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3015859229","https://openalex.org/W3159871278","https://openalex.org/W2230552005","https://openalex.org/W1975949872","https://openalex.org/W2905242764","https://openalex.org/W3109411864","https://openalex.org/W3017846737","https://openalex.org/W2656997359","https://openalex.org/W3003280185"],"abstract_inverted_index":{"Experimentation":[0],"using":[1],"IR":[2],"systems":[3],"has":[4],"traditionally":[5],"been":[6],"a":[7,81,88,104],"procedural":[8],"and":[9,52,66,162],"laborious":[10],"process.":[11],"Queries":[12],"must":[13],"be":[14,86,94,117],"run":[15],"on":[16],"an":[17,74,131],"index,":[18],"with":[19],"any":[20],"parameters":[21],"of":[22,31,40,73,90,123,145,167],"the":[23,29,37,56,71,108,120,165],"retrieval":[24,154,169],"models":[25],"suitably":[26],"tuned.":[27],"With":[28],"advent":[30],"learning-to-rank,":[32],"such":[33,62],"experimental":[34,50,75,121,133],"processes":[35],"(including":[36],"appropriate":[38],"folding":[39],"queries":[41],"to":[42,85,107,116,139],"achieve":[43],"cross-fold":[44],"validation)":[45],"have":[46,69],"resulted":[47],"in":[48,152,171],"complicated":[49],"designs":[51],"hence":[53],"scripting.":[54],"At":[55],"same":[57],"time,":[58],"machine":[59],"learning":[60],"platforms":[61],"as":[63],"Scikit":[64],"Learn":[65],"Apache":[67],"Spark":[68],"pioneered":[70],"notion":[72],"pipeline":[76],",":[77],"which":[78,92,113],"naturally":[79],"allows":[80],"supervised":[82],"classification":[83],"experiment":[84],"expressed":[87],"series":[89],"stages,":[91],"can":[93],"learned":[95],"or":[96],"transformed.":[97],"In":[98],"this":[99,128],"demonstration,":[100],"we":[101],"detail":[102],"Terrier-Spark,":[103],"recent":[105],"adaptation":[106],"Terrier":[109],"Information":[110],"Retrieval":[111],"platform":[112,134],"permits":[114],"it":[115],"used":[118],"within":[119],"pipelines":[122],"Spark.":[124],"We":[125],"argue":[126],"that":[127,140],"(1)":[129],"provides":[130],"agile":[132],"for":[135],"information":[136,153,168],"retrieval,":[137],"comparable":[138],"enjoyed":[141],"by":[142,155],"other":[143],"branches":[144],"data":[146],"science;":[147],"(2)":[148],"aids":[149],"research":[150],"reproducibility":[151],"facilitating":[156],"easily-distributable":[157],"notebooks":[158],"containing":[159],"conducted":[160],"experiments;":[161],"(3)":[163],"facilitates":[164],"teaching":[166],"experiments":[170],"educational":[172],"environments.":[173]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}