{"id":"https://openalex.org/W2887005207","doi":"https://doi.org/10.18653/v1/w18-3012","title":"Unsupervised Random Walk Sentence Embeddings: A Strong but Simple Baseline","display_name":"Unsupervised Random Walk Sentence Embeddings: A Strong but Simple Baseline","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2887005207","doi":"https://doi.org/10.18653/v1/w18-3012","mag":"2887005207"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-3012","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-3012","pdf_url":"https://www.aclweb.org/anthology/W18-3012.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 Third Workshop on Representation Learning for NLP","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-3012.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070411028","display_name":"Kawin Ethayarajh","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Kawin Ethayarajh","raw_affiliation_strings":["Department of Computer Science, University of Toronto"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070411028"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":10.661,"has_fulltext":true,"cited_by_count":95,"citation_normalized_percentile":{"value":0.98514995,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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":"Topic Modeling","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":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9900000095367432,"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/random-walk","display_name":"Random walk","score":0.8026020526885986},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6849828362464905},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6768738031387329},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.670183002948761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6295148134231567},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5881803631782532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5379669070243835},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49773576855659485},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.49200913310050964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3653673529624939},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.333878755569458},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12100619077682495}],"concepts":[{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.8026020526885986},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6849828362464905},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6768738031387329},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.670183002948761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6295148134231567},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5881803631782532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5379669070243835},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49773576855659485},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.49200913310050964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3653673529624939},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.333878755569458},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12100619077682495},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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:10.18653/v1/w18-3012","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-3012","pdf_url":"https://www.aclweb.org/anthology/W18-3012.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 Third Workshop on Representation Learning for NLP","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-3012","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-3012","pdf_url":"https://www.aclweb.org/anthology/W18-3012.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 Third Workshop on Representation Learning for NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G8284766523","display_name":null,"funder_award_id":"(NSERC)","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2887005207.pdf","grobid_xml":"https://content.openalex.org/works/W2887005207.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1486649854","https://openalex.org/W1814992895","https://openalex.org/W2091812280","https://openalex.org/W2103305545","https://openalex.org/W2117130368","https://openalex.org/W2120615054","https://openalex.org/W2126400076","https://openalex.org/W2131744502","https://openalex.org/W2133458109","https://openalex.org/W2137607259","https://openalex.org/W2140679639","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2251861449","https://openalex.org/W2251869843","https://openalex.org/W2251939518","https://openalex.org/W2463895987","https://openalex.org/W2518186251","https://openalex.org/W2605035112","https://openalex.org/W2606347107","https://openalex.org/W2751762827","https://openalex.org/W2752172973","https://openalex.org/W2770626128","https://openalex.org/W2963355447","https://openalex.org/W2963499246","https://openalex.org/W2963899155","https://openalex.org/W2963918774","https://openalex.org/W3104033643","https://openalex.org/W4285719527","https://openalex.org/W4294170691","https://openalex.org/W4295803813","https://openalex.org/W4313908941"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W3183136280","https://openalex.org/W4318559728","https://openalex.org/W2775233965","https://openalex.org/W3114716045","https://openalex.org/W4360995913"],"abstract_inverted_index":{"Using":[0],"a":[1,35,42,53],"random":[2,54],"walk":[3,55],"model":[4,56],"of":[5,41,66],"text":[6],"generation,":[7],"This":[8],"simple":[9],"method":[10],"even":[11],"outperforms":[12],"far":[13],"more":[14],"complex":[15],"approaches":[16],"such":[17],"as":[18],"LSTMs":[19],"on":[20,38,92],"textual":[21,93],"similarity":[22,94],"tasks.":[23],"In":[24],"this":[25,61],"paper,":[26],"we":[27],"first":[28],"show":[29],"that":[30,57],"word":[31,67,78],"vector":[32],"length":[33],"has":[34],"confounding":[36],"effect":[37],"the":[39,64,73,77],"probability":[40,65],"sentence":[43,80],"being":[44],"generated":[45],"in":[46],"Arora":[47,85,103],"et":[48,86,104],"al.'s":[49,87,105],"model.":[50],"We":[51],"propose":[52],"is":[58,69,97,120],"robust":[59],"to":[60,72,90],"confound,":[62],"where":[63],"generation":[68],"inversely":[70],"related":[71],"angular":[74],"distance":[75],"between":[76],"and":[79,96],"embeddings.":[81],"Our":[82],"approach":[83],"beats":[84],"by":[88],"up":[89],"44.4%":[91],"tasks":[95],"competitive":[98],"with":[99],"state-of-the-art":[100],"methods.":[101],"Unlike":[102],"method,":[106],"ours":[107],"requires":[108],"no":[109,121],"hyperparameter":[110],"tuning,":[111],"which":[112],"means":[113],"it":[114],"can":[115],"be":[116],"used":[117],"when":[118],"there":[119],"labelled":[122],"data.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":5}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}