{"id":"https://openalex.org/W2949034987","doi":"https://doi.org/10.18653/v1/p19-1153","title":"Towards Lossless Encoding of Sentences","display_name":"Towards Lossless Encoding of Sentences","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949034987","doi":"https://doi.org/10.18653/v1/p19-1153","mag":"2949034987"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1153","pdf_url":"https://www.aclweb.org/anthology/P19-1153.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1153.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017367036","display_name":"Gabriele Prato","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Gabriele Prato","raw_affiliation_strings":["Universit de Montral","Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Universit de Montral","institution_ids":[]},{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027238455","display_name":"Mathieu Duchesneau","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mathieu Duchesneau","raw_affiliation_strings":["Universit de Montral","Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Universit de Montral","institution_ids":[]},{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027720969","display_name":"Sarath Chandar","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sarath Chandar","raw_affiliation_strings":["Universit de Montral","Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Universit de Montral","institution_ids":[]},{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004382350","display_name":"Alain Tapp","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alain Tapp","raw_affiliation_strings":["Universit de Montral","Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Universit de Montral","institution_ids":[]},{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017367036"],"corresponding_institution_ids":["https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05251346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1577","last_page":"1583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9991000294685364,"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":0.9983000159263611,"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/lossless-compression","display_name":"Lossless compression","score":0.8561471700668335},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.8148549795150757},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7921350002288818},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7316386699676514},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6919472217559814},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6827677488327026},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6631676554679871},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5775686502456665},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5717180371284485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5542376637458801},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4498533010482788},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4293452501296997},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42760398983955383},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41748321056365967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36373957991600037},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.3345758616924286},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1681900918483734},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08169886469841003}],"concepts":[{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.8561471700668335},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8148549795150757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921350002288818},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7316386699676514},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6919472217559814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6827677488327026},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6631676554679871},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5775686502456665},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5717180371284485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5542376637458801},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4498533010482788},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4293452501296997},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42760398983955383},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41748321056365967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36373957991600037},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3345758616924286},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1681900918483734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08169886469841003},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/p19-1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1153","pdf_url":"https://www.aclweb.org/anthology/P19-1153.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.01659","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.01659","pdf_url":"https://arxiv.org/pdf/1906.01659","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2949034987","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/1906.01659.pdf","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:publications.polymtl.ca:46214","is_oa":false,"landing_page_url":"https://publications.polymtl.ca/46214/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Communication de conf\u00e9rence"},{"id":"doi:10.48550/arxiv.1906.01659","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.01659","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1153","pdf_url":"https://www.aclweb.org/anthology/P19-1153.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949034987.pdf","grobid_xml":"https://content.openalex.org/works/W2949034987.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W71795751","https://openalex.org/W1840435438","https://openalex.org/W1841724727","https://openalex.org/W1889268436","https://openalex.org/W1971844566","https://openalex.org/W2100495367","https://openalex.org/W2103305545","https://openalex.org/W2147800946","https://openalex.org/W2172140247","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2251939518","https://openalex.org/W2252215182","https://openalex.org/W2265846598","https://openalex.org/W2579166072","https://openalex.org/W2612953412","https://openalex.org/W2626778328","https://openalex.org/W2786685006","https://openalex.org/W2790235966","https://openalex.org/W2891521313","https://openalex.org/W2896457183","https://openalex.org/W2911109671","https://openalex.org/W2914526845","https://openalex.org/W2937297214","https://openalex.org/W2949300694","https://openalex.org/W2949433733","https://openalex.org/W2950726992","https://openalex.org/W2963012544","https://openalex.org/W2963846996"],"related_works":["https://openalex.org/W2962776659","https://openalex.org/W2757179985","https://openalex.org/W2540566554","https://openalex.org/W3133560342","https://openalex.org/W2409661879","https://openalex.org/W3143104624","https://openalex.org/W2325716904","https://openalex.org/W3202398375","https://openalex.org/W2900203667","https://openalex.org/W2747779981","https://openalex.org/W3139471157","https://openalex.org/W3175679307","https://openalex.org/W2955550261","https://openalex.org/W2566587499","https://openalex.org/W2518048962","https://openalex.org/W3008825656","https://openalex.org/W2963079584","https://openalex.org/W3035762680","https://openalex.org/W3190035338","https://openalex.org/W2995043393"],"abstract_inverted_index":{"A":[0],"lot":[1],"of":[2,10,26,91,97],"work":[3],"has":[4,20,45],"been":[5,21],"done":[6],"in":[7],"the":[8,24,71,75],"field":[9],"image":[11],"compression":[12,25],"via":[13],"machine":[14],"learning,":[15],"but":[16],"not":[17,40],"much":[18],"attention":[19],"given":[22],"to":[23,51,68],"natural":[27],"language.":[28],"Compressing":[29],"text":[30],"into":[31,100],"lossless":[32,85],"representations":[33],"while":[34],"making":[35],"features":[36],"easily":[37],"retrievable":[38],"is":[39],"a":[41,83],"trivial":[42],"task,":[43],"yet":[44],"huge":[46],"benefits.":[47],"Most":[48],"methods":[49],"designed":[50],"produce":[52],"feature":[53,101],"rich":[54,102],"sentence":[55,119],"embeddings":[56],"focus":[57],"solely":[58],"on":[59,62,108],"performing":[60],"well":[61,94],"downstream":[63],"tasks":[64],"and":[65,111,118],"are":[66],"unable":[67],"properly":[69],"reconstruct":[70],"original":[72],"sequence":[73],"from":[74],"learned":[76],"embedding.":[77],"In":[78],"this":[79],"work,":[80],"we":[81],"propose":[82],"near":[84],"method":[86,107],"for":[87],"encoding":[88],"long":[89],"sequences":[90],"texts":[92],"as":[93,95],"all":[96,116],"their":[98],"sub-sequences":[99],"representations.":[103],"We":[104],"test":[105],"our":[106],"sentiment":[109],"analysis":[110],"show":[112],"good":[113],"performance":[114],"across":[115],"sub-sentence":[117],"embeddings.":[120]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}