{"id":"https://openalex.org/W2953774736","doi":"https://doi.org/10.1145/3331184.3331344","title":"On the Effect of Low-Frequency Terms on Neural-IR Models","display_name":"On the Effect of Low-Frequency Terms on Neural-IR Models","publication_year":2019,"publication_date":"2019-07-18","ids":{"openalex":"https://openalex.org/W2953774736","doi":"https://doi.org/10.1145/3331184.3331344","mag":"2953774736"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3331184.3331344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.12683","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089466895","display_name":"Sebastian Hofst\u00e4tter","orcid":"https://orcid.org/0009-0006-1229-2612"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sebastian Hofst\u00e4tter","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017877491","display_name":"Navid Rekabsaz","orcid":"https://orcid.org/0000-0001-5764-8738"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Navid Rekabsaz","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014921416","display_name":"Carsten Eickhoff","orcid":"https://orcid.org/0000-0001-9895-4061"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]},{"id":"https://openalex.org/I196272386","display_name":"Providence College","ror":"https://ror.org/00rxpqe74","country_code":"US","type":"education","lineage":["https://openalex.org/I196272386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carsten Eickhoff","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330","https://openalex.org/I196272386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020665735","display_name":"Allan Hanbury","orcid":"https://orcid.org/0000-0002-7149-5843"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Allan Hanbury","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institution_assertions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.969,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":32,"citation_normalized_percentile":{"value":0.999907,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Natural Language Processing","score":1.0,"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":"Natural Language Processing","score":1.0,"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":"Statistical Machine Translation and Natural Language Processing","score":0.9996,"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 Techniques and Evaluation","score":0.9975,"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/robustness","display_name":"Robustness (evolution)","score":0.6528226},{"id":"https://openalex.org/keywords/language-modeling","display_name":"Language Modeling","score":0.519842},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information Retrieval","score":0.514097},{"id":"https://openalex.org/keywords/neural-machine-translation","display_name":"Neural Machine Translation","score":0.510199},{"id":"https://openalex.org/keywords/topic-modeling","display_name":"Topic Modeling","score":0.508082},{"id":"https://openalex.org/keywords/word-representation","display_name":"Word Representation","score":0.502618}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436568},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6528226},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.63103604},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5199672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5077823},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46971267},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42647764},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41110674},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35371047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33588547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10124388},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3331184.3331344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1904.12683","pdf_url":"https://arxiv.org/pdf/1904.12683","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1904.12683","pdf_url":"https://arxiv.org/pdf/1904.12683","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.75}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":14,"referenced_works":["https://openalex.org/W2004329216","https://openalex.org/W2250539671","https://openalex.org/W2405884322","https://openalex.org/W2493916176","https://openalex.org/W2537776792","https://openalex.org/W2648699835","https://openalex.org/W2740321901","https://openalex.org/W2740851615","https://openalex.org/W2783640434","https://openalex.org/W2798984085","https://openalex.org/W2897754576","https://openalex.org/W2929149158","https://openalex.org/W2962739339","https://openalex.org/W3102779043"],"related_works":["https://openalex.org/W4385572700","https://openalex.org/W4385009901","https://openalex.org/W4307309205","https://openalex.org/W4288261899","https://openalex.org/W4285141722","https://openalex.org/W3134175397","https://openalex.org/W2997152889","https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W1997182898"],"abstract_inverted_index":{"Low-frequency":[0],"terms":[1,23,60],"are":[2,24],"a":[3,33,82,132,140],"recurring":[4],"challenge":[5],"for":[6,97,162,200],"information":[7],"retrieval":[8,85],"models,":[9,79,157],"especially":[10],"neural":[11,28,67,77,90,163,181],"IR":[12,49,68,78,91,164,182],"frameworks":[13],"struggle":[14],"with":[15,93],"adequately":[16],"capturing":[17],"infrequently":[18],"observed":[19],"words.":[20],"While":[21],"these":[22],"often":[25],"removed":[26],"from":[27],"models":[29,92,183,187],"-":[30,38],"mainly":[31],"as":[32],"concession":[34],"to":[35,131,147,175,186],"efficiency":[36],"demands":[37],"they":[39],"traditionally":[40],"play":[41],"an":[42],"important":[43],"role":[44],"in":[45,159,184],"the":[46,56,62,89,108,116,123,127,143,152,176,180,190,194],"performance":[47,63,124,178],"of":[48,58,66,105,119,139,145,154,179],"models.":[50,69,165],"In":[51],"this":[52],"paper,":[53],"we":[54],"analyze":[55],"effects":[57],"low-frequency":[59,203],"on":[61,74,81,107,189],"and":[64,158],"robustness":[65],"We":[70,87,112,149],"conduct":[71],"controlled":[72],"experiments":[73,167],"three":[75],"recent":[76],"trained":[80,188],"large-scale":[83],"passage":[84],"collection.":[86],"evaluate":[88],"various":[94],"vocabulary":[95],"sizes":[96],"their":[98],"respective":[99],"word":[100],"embeddings,":[101],"considering":[102],"different":[103],"levels":[104],"constraints":[106],"available":[109],"GPU":[110],"memory.":[111],"observe":[113],"that":[114,169],"despite":[115],"significant":[117],"benefits":[118],"using":[120,170],"larger":[121],"vocabularies,":[122],"gap":[125],"between":[126],"vocabularies":[128],"can":[129],"be,":[130],"great":[133],"extent,":[134],"mitigated":[135],"by":[136],"extensive":[137],"tuning":[138],"related":[141],"parameter:":[142],"number":[144],"documents":[146],"re-rank.":[148],"further":[150],"investigate":[151],"use":[153],"subword-token":[155],"embedding":[156],"particular":[160],"FastText,":[161],"Our":[166],"show":[168],"FastText":[171],"brings":[172],"slight":[173],"improvements":[174],"overall":[177],"comparison":[185],"full":[191],"vocabulary,":[192],"while":[193],"improvement":[195],"becomes":[196],"much":[197],"more":[198],"pronounced":[199],"queries":[201],"containing":[202],"terms.":[204]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2953774736","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":4}],"updated_date":"2024-11-28T12:25:38.319212","created_date":"2019-07-12"}