{"id":"https://openalex.org/W2952997929","doi":"https://doi.org/10.48550/arxiv.1808.09935","title":"Attention-based Neural Text Segmentation","display_name":"Attention-based Neural Text Segmentation","publication_year":2018,"publication_date":"2018-08-29","ids":{"openalex":"https://openalex.org/W2952997929","doi":"https://doi.org/10.48550/arxiv.1808.09935","mag":"2952997929"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1808.09935","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.09935","pdf_url":"https://arxiv.org/pdf/1808.09935","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1808.09935","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000852149","display_name":"Pinkesh Badjatiya","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Badjatiya, Pinkesh","raw_affiliation_strings":["IIIT-H , Hyderabad , India","IIIT-H"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-H , Hyderabad , India","institution_ids":["https://openalex.org/I64189192"]},{"raw_affiliation_string":"IIIT-H","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064537261","display_name":"Litton J Kurisinkel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kurisinkel, Litton J","raw_affiliation_strings":["IIIT-H"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-H","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046755750","display_name":"Manish Gupta","orcid":"https://orcid.org/0000-0002-2843-3110","observed_orcids":["https://orcid.org/0000-0002-2843-3110"]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gupta, Manish","raw_affiliation_strings":["IIIT-H"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-H","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073786634","display_name":"Vasudeva Varma","orcid":"https://orcid.org/0000-0003-1923-1725","observed_orcids":["https://orcid.org/0000-0003-1923-1725"]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Varma, Vasudeva","raw_affiliation_strings":["IIIT-H"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-H","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"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":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.923799991607666,"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":0.923799991607666,"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":0.0568000003695488,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.00570000009611249,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/text-segmentation","display_name":"text segmentation","score":0.996999979019165},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.8569999933242798},{"id":"https://openalex.org/keywords/bidirectional-lstm","display_name":"bidirectional LSTM","score":1.0},{"id":"https://openalex.org/keywords/sentence-embeddings","display_name":"sentence embeddings","score":0.8180000185966492},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.828000009059906},{"id":"https://openalex.org/keywords/contextual-information","display_name":"contextual information","score":0.6589999794960022},{"id":"https://openalex.org/keywords/document-indexing","display_name":"document indexing","score":0.4749999940395355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8626551032066345},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7443720698356628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6915675401687622},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6560090780258179},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.60055011510849},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5971511602401733},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.593216061592102},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5887902975082397},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5812506079673767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5391559600830078},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5256391763687134},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5179216265678406},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42644476890563965},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41535013914108276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39457839727401733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34701764583587646},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32319653034210205},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1808.09935","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.09935","pdf_url":"https://arxiv.org/pdf/1808.09935","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1808.09935","doi":"https://doi.org/10.48550/arxiv.1808.09935","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.09935","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1808.09935","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.09935","pdf_url":"https://arxiv.org/pdf/1808.09935","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952997929.pdf","grobid_xml":"https://content.openalex.org/works/W2952997929.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W887185921","https://openalex.org/W1514535095","https://openalex.org/W1557074680","https://openalex.org/W1582784770","https://openalex.org/W1828401780","https://openalex.org/W1843891098","https://openalex.org/W1862888253","https://openalex.org/W2064675550","https://openalex.org/W2096476966","https://openalex.org/W2106918957","https://openalex.org/W2118612506","https://openalex.org/W2124585778","https://openalex.org/W2140836433","https://openalex.org/W2148818577","https://openalex.org/W2159083595","https://openalex.org/W2161793958","https://openalex.org/W2164439758","https://openalex.org/W2211192759","https://openalex.org/W2559122826","https://openalex.org/W2761764495","https://openalex.org/W2787554544"],"related_works":["https://openalex.org/W3198035914","https://openalex.org/W3092628869","https://openalex.org/W2807938752","https://openalex.org/W3014723908","https://openalex.org/W4388740291","https://openalex.org/W2997244287","https://openalex.org/W4242454016","https://openalex.org/W4411811241","https://openalex.org/W2794904608","https://openalex.org/W3163508711"],"abstract_inverted_index":{"Text":[0],"segmentation":[1],"plays":[2],"an":[3,64],"important":[4],"role":[5],"in":[6,109],"various":[7],"Natural":[8],"Language":[9],"Processing":[10],"(NLP)":[11],"tasks":[12],"like":[13],"summarization,":[14],"context":[15,92],"understanding,":[16],"document":[17,20],"indexing":[18],"and":[19,35,76],"noise":[21],"removal.":[22],"Previous":[23],"methods":[24],"for":[25,58],"this":[26,45],"task":[27],"require":[28],"manual":[29],"feature":[30],"engineering,":[31],"huge":[32],"memory":[33],"requirements":[34],"large":[36],"execution":[37],"times.":[38],"To":[39],"the":[40,48,77,96,100],"best":[41],"of":[42,107],"our":[43],"knowledge,":[44],"paper":[46],"is":[47],"first":[49],"one":[50],"to":[51,95],"present":[52],"a":[53,104],"novel":[54],"supervised":[55],"neural":[56],"approach":[57],"text":[59],"segmentation.":[60],"Specifically,":[61],"we":[62],"propose":[63],"attention-based":[65],"bidirectional":[66],"LSTM":[67],"model":[68,86,102],"where":[69],"sentence":[70],"embeddings":[71],"are":[72,79],"learned":[73],"using":[74],"CNNs":[75],"segments":[78],"predicted":[80],"based":[81],"on":[82,112],"contextual":[83],"information.":[84,93],"This":[85],"can":[87],"automatically":[88],"handle":[89],"variable":[90],"sized":[91],"Compared":[94],"existing":[97],"competitive":[98],"baselines,":[99],"proposed":[101],"shows":[103],"performance":[105],"improvement":[106],"~7%":[108],"WinDiff":[110],"score":[111],"three":[113],"benchmark":[114],"datasets.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-06-27T00:00:00"}