{"id":"https://openalex.org/W4412673523","doi":"https://doi.org/10.1145/3731120.3744593","title":"Zero-Shot and Hybrid Strategies for Tetun Ad-Hoc Text Retrieval","display_name":"Zero-Shot and Hybrid Strategies for Tetun Ad-Hoc Text Retrieval","publication_year":2025,"publication_date":"2025-07-18","ids":{"openalex":"https://openalex.org/W4412673523","doi":"https://doi.org/10.1145/3731120.3744593"},"language":"en","primary_location":{"id":"doi:10.1145/3731120.3744593","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731120.3744593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-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/A5103068563","display_name":"Gabriel de Jes\u00fas","orcid":"https://orcid.org/0000-0003-4392-2382"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]},{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Gabriel de Jesus","raw_affiliation_strings":["INESC TEC / University of Porto, Porto, Portugal"],"affiliations":[{"raw_affiliation_string":"INESC TEC / University of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113848812","display_name":"Satendra Singh","orcid":"https://orcid.org/0009-0009-8835-5845"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Siddharth A.K. Singh","raw_affiliation_strings":["IRLab / University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"IRLab / University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065124975","display_name":"S\u00e9rgio Nunes","orcid":"https://orcid.org/0000-0002-2693-988X"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]},{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"S\u00e9rgio Nunes","raw_affiliation_strings":["INESC TEC / University of Porto, Porto, Portugal"],"affiliations":[{"raw_affiliation_string":"INESC TEC / University of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I182534213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059489981","display_name":"Andrew Yates","orcid":"https://orcid.org/0000-0002-5970-880X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Yates","raw_affiliation_strings":["HLTCOE / Johns Hopkins University, Baltimore, Maryland, USA"],"affiliations":[{"raw_affiliation_string":"HLTCOE / Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I2799853436","https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103068563"],"corresponding_institution_ids":["https://openalex.org/I182534213","https://openalex.org/I4210166615"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09048594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"264","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.6894997954368591},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6423051357269287},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5987915992736816},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34655168652534485},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06080430746078491},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.055674970149993896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894997954368591},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6423051357269287},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5987915992736816},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34655168652534485},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06080430746078491},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.055674970149993896},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731120.3744593","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731120.3744593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1845198550","https://openalex.org/W2065240770","https://openalex.org/W2105157020","https://openalex.org/W2148972377","https://openalex.org/W2897879263","https://openalex.org/W2963341956","https://openalex.org/W2964517691","https://openalex.org/W2979826702","https://openalex.org/W3021397474","https://openalex.org/W3045745713","https://openalex.org/W3099700870","https://openalex.org/W3100107515","https://openalex.org/W3104914963","https://openalex.org/W3137305332","https://openalex.org/W3145630588","https://openalex.org/W3188983256","https://openalex.org/W3208821253","https://openalex.org/W3216225167","https://openalex.org/W3217305727","https://openalex.org/W4205103289","https://openalex.org/W4226208814","https://openalex.org/W4226325130","https://openalex.org/W4252076394","https://openalex.org/W4252222626","https://openalex.org/W4327644092","https://openalex.org/W4385571614","https://openalex.org/W4385780698","https://openalex.org/W4386488973","https://openalex.org/W4388955690","https://openalex.org/W4389524402","https://openalex.org/W4391840390","https://openalex.org/W4404317962","https://openalex.org/W4404782892","https://openalex.org/W6927022540","https://openalex.org/W6941932227","https://openalex.org/W6964713768"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W4411535265","https://openalex.org/W2980279061","https://openalex.org/W2334685461"],"abstract_inverted_index":{"Dense":[0],"retrieval":[1,48,77,113,119,129,143,204,230],"models":[2,24,49,78,97,130,144],"are":[3],"generally":[4],"trained":[5],"using":[6,179],"supervised":[7],"learning":[8],"approaches":[9],"for":[10,30,53,69,115,146,195],"representation":[11],"learning,":[12],"which":[13],"require":[14],"a":[15,155,159,215],"labeled":[16,67],"dataset":[17],"(i.e.,":[18],"query-document":[19],"pairs).":[20],"However,":[21],"training":[22],"such":[23],"from":[25,220],"scratch":[26],"is":[27],"not":[28,80],"feasible":[29],"most":[31,125],"languages,":[32],"particularly":[33],"under-resourced":[34],"ones,":[35],"due":[36],"to":[37,98,104,184],"data":[38,68],"scarcity":[39],"and":[40,71,112,169,182,205,244],"computational":[41],"constraints.":[42],"As":[43],"an":[44],"alternative,":[45],"pretrained":[46,126],"dense":[47,76,128,142],"can":[50],"be":[51],"fine-tuned":[52],"specific":[54],"downstream":[55],"tasks":[56],"or":[57],"applied":[58],"directly":[59],"in":[60,90,135,154,164,167,171,202,232],"zero-shot":[61,102],"settings.":[62],"Given":[63,138],"the":[64,72,83,116,139,174,196,221,226,240],"lack":[65,140],"of":[66,141,162,228],"Tetun":[70,99],"fact":[73],"that":[74,124,207],"existing":[75],"do":[79],"currently":[81],"support":[82,235],"language,":[84],"this":[85],"study":[86],"investigates":[87],"their":[88,106,132],"application":[89],"zero-shot,":[91],"out-of-distribution":[92],"scenarios.":[93],"We":[94,190],"adapted":[95],"these":[96],"documents,":[100],"producing":[101],"embeddings,":[103],"evaluate":[105],"performance":[107,227],"across":[108],"various":[109,136],"document":[110,209,242],"representations":[111],"strategies":[114,231],"ad-hoc":[117],"text":[118],"task.":[120],"The":[121],"results":[122],"show":[123],"monolingual":[127],"outperformed":[131],"multilingual":[133],"counterparts":[134],"configurations.":[137],"specialized":[145],"Tetun,":[147],"we":[148,237],"combine":[149],"Hiemstra":[150],"LM":[151],"with":[152,211],"ColBERTv2":[153],"hybrid":[156,203,229],"strategy,":[157],"achieving":[158],"relative":[160],"improvement":[161],"+2.01%":[163],"P@10,":[165],"+4.24%":[166],"MAP@10,":[168],"+2.45%":[170],"NDCG@10":[172],"over":[173],"baseline,":[175],"based":[176],"on":[177],"evaluations":[178],"59":[180],"queries":[181],"up":[183],"2,000":[185],"retrieved":[186],"documents":[187],"per":[188],"query.":[189],"propose":[191],"dual":[192],"tuning":[193],"parameters":[194],"score":[197],"fusion":[198],"approach":[199],"commonly":[200],"used":[201],"demonstrate":[206],"enriching":[208],"titles":[210],"summaries":[212,243],"generated":[213],"by":[214],"large":[216],"language":[217],"model":[218],"(LLM)":[219],"documents'":[222],"content":[223],"significantly":[224],"enhances":[225],"Tetun.":[233],"To":[234],"reproducibility,":[236],"publicly":[238],"release":[239],"LLM-generated":[241],"run":[245],"files.":[246]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}