{"id":"https://openalex.org/W6999905145","doi":null,"title":"Distinguishing Noise and Main Text Content from Web-Sourced Plain Text Documents Using Sequential Neural Networks","display_name":"Distinguishing Noise and Main Text Content from Web-Sourced Plain Text Documents Using Sequential Neural Networks","publication_year":2022,"publication_date":"2022-05-04","ids":{"openalex":"https://openalex.org/W6999905145"},"language":"en","primary_location":{"id":"pmh:oai:utupub.fi:11111/16240","doi":null,"is_oa":true,"landing_page_url":"https://www.utupub.fi/handle/11111/16240","pdf_url":"https://www.utupub.fi/bitstreams/4f04cd90-8d50-4061-acaa-c67b77c5fdb1/download","source":{"id":"https://openalex.org/S4306402470","display_name":"UTUPub (University of Turku)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I155660961","host_organization_name":"University of Turku","host_organization_lineage":["https://openalex.org/I155660961"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.utupub.fi/handle/10024/154040","raw_type":"fi=Pro gradu -tutkielma|en=Master's thesis|"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.utupub.fi/bitstreams/4f04cd90-8d50-4061-acaa-c67b77c5fdb1/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Salmela, Anna","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Salmela, Anna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7734000086784363,"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":0.7734000086784363,"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":0.07819999754428864,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.03180000185966492,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/xlm-r","display_name":"XLM-R","score":0.8479999899864197},{"id":"https://openalex.org/keywords/multilingual-pretrained-language-models","display_name":"multilingual pretrained language models","score":0.7289999723434448},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.9490000009536743},{"id":"https://openalex.org/keywords/lstm","display_name":"LSTM","score":0.5239999890327454},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.7929999828338623},{"id":"https://openalex.org/keywords/text-cleaning","display_name":"text cleaning","score":0.4269999861717224},{"id":"https://openalex.org/keywords/french-language","display_name":"French language","score":0.4909999966621399},{"id":"https://openalex.org/keywords/swedish-language","display_name":"Swedish language","score":0.9039999842643738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893999814987183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6312000155448914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6126999855041504},{"id":"https://openalex.org/C46503548","wikidata":"https://www.wikidata.org/wiki/Q1145976","display_name":"Plain text","level":3,"score":0.5910000205039978},{"id":"https://openalex.org/C75701414","wikidata":"https://www.wikidata.org/wiki/Q1651672","display_name":"Boilerplate text","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4837999939918518},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.37310001254081726},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.33809998631477356},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:utupub.fi:11111/16240","doi":null,"is_oa":true,"landing_page_url":"https://www.utupub.fi/handle/11111/16240","pdf_url":"https://www.utupub.fi/bitstreams/4f04cd90-8d50-4061-acaa-c67b77c5fdb1/download","source":{"id":"https://openalex.org/S4306402470","display_name":"UTUPub (University of Turku)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I155660961","host_organization_name":"University of Turku","host_organization_lineage":["https://openalex.org/I155660961"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.utupub.fi/handle/10024/154040","raw_type":"fi=Pro gradu -tutkielma|en=Master's thesis|"},{"id":"pmh:oai:www.utupub.fi:10024/154040","doi":null,"is_oa":false,"landing_page_url":"https://www.utupub.fi/handle/10024/154040","pdf_url":null,"source":{"id":"https://openalex.org/S4306402470","display_name":"UTUPub (University of Turku)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I155660961","host_organization_name":"University of Turku","host_organization_lineage":["https://openalex.org/I155660961"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"fi=Pro gradu -tutkielma|en=Master's thesis|"}],"best_oa_location":{"id":"pmh:oai:utupub.fi:11111/16240","doi":null,"is_oa":true,"landing_page_url":"https://www.utupub.fi/handle/11111/16240","pdf_url":"https://www.utupub.fi/bitstreams/4f04cd90-8d50-4061-acaa-c67b77c5fdb1/download","source":{"id":"https://openalex.org/S4306402470","display_name":"UTUPub (University of Turku)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I155660961","host_organization_name":"University of Turku","host_organization_lineage":["https://openalex.org/I155660961"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.utupub.fi/handle/10024/154040","raw_type":"fi=Pro gradu -tutkielma|en=Master's thesis|"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6999905145.pdf","grobid_xml":"https://content.openalex.org/works/W6999905145.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1940872118","https://openalex.org/W1995341919","https://openalex.org/W2040870580","https://openalex.org/W2053831280","https://openalex.org/W2064675550","https://openalex.org/W2133564696","https://openalex.org/W2134943861","https://openalex.org/W2509446521","https://openalex.org/W2625465398","https://openalex.org/W2626778328","https://openalex.org/W2782975741","https://openalex.org/W2794888134","https://openalex.org/W2896457183","https://openalex.org/W2898796642","https://openalex.org/W2964583233","https://openalex.org/W2970049541","https://openalex.org/W2994980856","https://openalex.org/W2995647371","https://openalex.org/W3013437827","https://openalex.org/W3016888273","https://openalex.org/W3021347373","https://openalex.org/W3032816972","https://openalex.org/W3040245432","https://openalex.org/W3132928422","https://openalex.org/W3177057043","https://openalex.org/W4221165895"],"related_works":["https://openalex.org/W2551443317","https://openalex.org/W2467373585","https://openalex.org/W3031678783","https://openalex.org/W7078797679","https://openalex.org/W4405511346","https://openalex.org/W4410825380","https://openalex.org/W4386862694","https://openalex.org/W4285416269","https://openalex.org/W4389520338","https://openalex.org/W3120697923"],"abstract_inverted_index":{"Boilerplate":[0],"removal":[1],"and":[2,28,61,74,89,117,144,166,201],"the":[3,6,25,48,101,113,134,138,141,145,164,169,172,176],"identification":[4],"of":[5,112,140,171,185],"actual":[7],"textual":[8,50],"content":[9,51],"is":[10],"a":[11,66,80,106,118,160],"crucial":[12],"step":[13],"in":[14,52,154,198],"web":[15],"corpus":[16],"creation.":[17],"However,":[18],"existing":[19],"methods":[20,45],"don\u2019t":[21],"always":[22],"filter":[23],"out":[24],"noise":[26],"perfectly":[27],"are":[29],"often":[30],"not":[31],"applicable":[32],"for":[33,68,206],"plain":[34,53],"text":[35,54,181,186],"corpora.":[36],"In":[37],"this":[38],"thesis,":[39],"I":[40,56,92,130,157],"will":[41,57,93,131,158],"develop":[42],"machine":[43,96],"learning":[44,60,97],"to":[46,209,218],"identify":[47],"main":[49],"documents.":[55],"utilize":[58],"transfer":[59],"pretrained":[62,114],"language":[63,103],"models":[64,71,178],"as":[65,77,79,189],"base":[67],"training":[69],"monolingual":[70],"with":[72,83,152,175,180],"French":[73],"Swedish":[75],"data":[76,153,213],"well":[78,150],"multilingual":[81,147],"model":[82,108,116,120,143,148],"French,":[84],"Swedish,":[85],"English,":[86],"Finnish,":[87],"German":[88],"Spanish":[90],"data.":[91],"compare":[94],"two":[95],"architectures":[98],"based":[99],"on":[100,110,163,211],"XLM-RoBERTa":[102,115,142],"model:":[104],"first":[105],"classification":[107,139],"built":[109,146],"top":[111],"second":[119],"using":[121],"an":[122],"additional":[123],"Long":[124],"Short-Term":[125],"Memory":[126],"(LSTM)":[127],"network":[128],"layer.":[129],"show":[132,167],"that":[133,168,214],"LSTM":[135],"layer":[136],"improves":[137],"performs":[149],"even":[151],"unseen":[155],"languages.":[156],"perform":[159],"further":[161],"analysis":[162],"results":[165,170],"boilerplate":[173,199],"detection":[174],"trained":[177],"differ":[179],"varieties.":[182],"Certain":[183],"types":[184],"documents,":[187],"such":[188],"lyrical":[190],"texts":[191,195],"or":[192],"discussion":[193],"forum":[194],"pose":[196],"challenges":[197],"detection,":[200],"it":[202],"would":[203],"be":[204],"beneficial":[205],"future":[207],"research":[208],"focus":[210],"gathering":[212],"has":[215],"been":[216],"difficult":[217],"clean.":[219]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}