{"id":"https://openalex.org/W2574026469","doi":null,"title":"Building a Monolingual Parallel Corpus for Text Simplification Using Sentence Similarity Based on Alignment between Word Embeddings.","display_name":"Building a Monolingual Parallel Corpus for Text Simplification Using Sentence Similarity Based on Alignment between Word Embeddings.","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2574026469","mag":"2574026469"},"language":"en","primary_location":{"id":"mag:2574026469","doi":null,"is_oa":false,"landing_page_url":"https://aclanthology.org/C16-1109/","pdf_url":null,"source":{"id":"https://openalex.org/S4306419219","display_name":"International Conference on Computational Linguistics","issn_l":"1525-2477","issn":["1525-2477"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Computational Linguistics","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5006117547","display_name":"Tomoyuki Kajiwara","orcid":"https://orcid.org/0000-0002-3233-4879","observed_orcids":["https://orcid.org/0000-0002-3233-4879"]},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyuki Kajiwara","raw_affiliation_strings":["Tokyo Metropolitan University, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3233-4879","affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061931124","display_name":"Mamoru Komachi","orcid":"https://orcid.org/0000-0003-1166-1739","observed_orcids":["https://orcid.org/0000-0003-1166-1739"]},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mamoru Komachi","raw_affiliation_strings":["Tokyo Metropolitan University, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1166-1739","affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":20.823,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.98758621,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1147","last_page":"1158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.763700008392334,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.763700008392334,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.22310000658035278,"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/T10028","display_name":"Topic Modeling","score":0.005499999970197678,"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/text-simplification","display_name":"text simplification","score":0.9729999899864197},{"id":"https://openalex.org/keywords/sentence-similarity","display_name":"sentence similarity","score":0.9229999780654907},{"id":"https://openalex.org/keywords/word-embeddings","display_name":"word embeddings","score":0.9760000109672546},{"id":"https://openalex.org/keywords/word-alignment","display_name":"word alignment","score":0.9279999732971191},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.7919999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8492668867111206},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.812271237373352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7537354230880737},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7389581799507141},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6738969087600708},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6427903175354004},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6320956349372864},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.53360515832901},{"id":"https://openalex.org/C59415355","wikidata":"https://www.wikidata.org/wiki/Q3484781","display_name":"Text simplification","level":3,"score":0.5077670812606812},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.45893949270248413},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4585350453853607},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.42716217041015625},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.42711713910102844},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14674112200737},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2574026469","doi":null,"is_oa":false,"landing_page_url":"https://aclanthology.org/C16-1109/","pdf_url":null,"source":{"id":"https://openalex.org/S4306419219","display_name":"International Conference on Computational Linguistics","issn_l":"1525-2477","issn":["1525-2477"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Computational Linguistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1544285860","https://openalex.org/W1614298861","https://openalex.org/W1746111881","https://openalex.org/W2101105183","https://openalex.org/W2109802560","https://openalex.org/W2124807415","https://openalex.org/W2125101937","https://openalex.org/W2126400076","https://openalex.org/W2133458109","https://openalex.org/W2134800885","https://openalex.org/W2138238299","https://openalex.org/W2146574666","https://openalex.org/W2152180407","https://openalex.org/W2153579005","https://openalex.org/W2156422881","https://openalex.org/W2156985047","https://openalex.org/W2162130683","https://openalex.org/W2222512263","https://openalex.org/W2251312762","https://openalex.org/W2251831371","https://openalex.org/W2251861449","https://openalex.org/W2251916238","https://openalex.org/W2251933807","https://openalex.org/W2252010905","https://openalex.org/W2252150696","https://openalex.org/W2292232452","https://openalex.org/W2294556942","https://openalex.org/W2296307963","https://openalex.org/W2406289639"],"related_works":["https://openalex.org/W3169540523","https://openalex.org/W3198803846","https://openalex.org/W2534253848","https://openalex.org/W3011585284","https://openalex.org/W2807539165","https://openalex.org/W7166543059","https://openalex.org/W2889577057","https://openalex.org/W3023237241","https://openalex.org/W2981174942","https://openalex.org/W4220925714"],"abstract_inverted_index":{"Methods":[0],"for":[1,25,36,44,59,74,145],"text":[2,37,75,147,157],"simplification":[3,38,76,158],"using":[4,77,168,178],"the":[5,20,27,57,70,106,110,115,131,135,153,161,169,173,179],"framework":[6,162],"of":[7,48,101,134,163],"statistical":[8,164],"machine":[9,165],"translation":[10,166],"have":[11,39],"been":[12,41],"extensively":[13],"studied":[14],"in":[15,105,114,138,156],"recent":[16],"years.":[17],"However,":[18],"building":[19],"monolingual":[21,71,140],"parallel":[22,34,72,141],"corpus":[23,73,142,170],"necessary":[24],"training":[26],"model":[28],"requires":[29],"costly":[30],"human":[31,60],"annotation.":[32],"Monolingual":[33],"corpora":[35],"therefore":[40],"built":[42,171],"only":[43],"a":[45,89,98,139],"limited":[46],"number":[47],"languages,":[49],"such":[50],"as":[51],"English":[52,146],"and":[53,92,118],"Portuguese.":[54],"To":[55],"obviate":[56],"need":[58],"annotation,":[61],"we":[62,96],"propose":[63],"an":[64],"unsupervised":[65],"method":[66,100,137,175],"that":[67,159,177],"automatically":[68],"builds":[69],"sentence":[78,86,91,108,117,120],"similarity":[79,121],"based":[80],"on":[81],"word":[82,104,113,125],"embeddings.":[83],"For":[84],"any":[85],"pair":[87],"comprising":[88],"complex":[90,107],"its":[93],"simple":[94,116],"counterpart,":[95],"employ":[97],"many-to-one":[99],"aligning":[102],"each":[103],"with":[109],"most":[111],"similar":[112],"compute":[119],"by":[122,172],"averaging":[123],"these":[124],"similarities.":[126],"The":[127,149],"experimental":[128],"results":[129,150],"demonstrate":[130],"excellent":[132],"performance":[133],"proposed":[136,174],"construction":[143],"task":[144],"simplification.":[148],"also":[151],"demonstrated":[152],"superior":[154],"accuracy":[155],"use":[160],"trained":[167],"to":[176],"existing":[180],"corpora.":[181]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":9}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2017-01-26T00:00:00"}