{"id":"https://openalex.org/W4389520028","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.106","title":"Learning to Abstract with Nonparametric Variational Information Bottleneck","display_name":"Learning to Abstract with Nonparametric Variational Information Bottleneck","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389520028","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.106"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.106","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-emnlp.106","pdf_url":"https://aclanthology.org/2023.findings-emnlp.106.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.findings-emnlp.106.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025234653","display_name":"Melika Behjati","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Melika Behjati","raw_affiliation_strings":["Idiap Research Institute, Switzerland","\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067581142","display_name":"Fabio Fehr","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fabio Fehr","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","Idiap Research Institute, Switzerland"],"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084321238","display_name":"James Henderson","orcid":"https://orcid.org/0000-0003-3714-4799"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"James Henderson","raw_affiliation_strings":["Idiap Research Institute, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025234653"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16681614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1576","last_page":"1586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9715999960899353,"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/information-bottleneck-method","display_name":"Information bottleneck method","score":0.7593965530395508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7500406503677368},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6859056949615479},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5497088432312012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5401818156242371},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5302060842514038},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5248560905456543},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5210018754005432},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.48482978343963623},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4467231035232544},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4327065944671631},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.431182324886322},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42635378241539},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.41517969965934753},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3715474009513855},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.19603469967842102},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1438758671283722}],"concepts":[{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.7593965530395508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500406503677368},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6859056949615479},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5497088432312012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5401818156242371},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5302060842514038},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5248560905456543},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5210018754005432},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.48482978343963623},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4467231035232544},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4327065944671631},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.431182324886322},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42635378241539},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.41517969965934753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3715474009513855},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.19603469967842102},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1438758671283722},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.findings-emnlp.106","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-emnlp.106","pdf_url":"https://aclanthology.org/2023.findings-emnlp.106.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.106","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-emnlp.106","pdf_url":"https://aclanthology.org/2023.findings-emnlp.106.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389520028.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2121879602","https://openalex.org/W2250539671","https://openalex.org/W2753738274","https://openalex.org/W2767899794","https://openalex.org/W2790235966","https://openalex.org/W2804802260","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2963088785","https://openalex.org/W2963250244","https://openalex.org/W2963341956","https://openalex.org/W2963735467","https://openalex.org/W2963899393","https://openalex.org/W2964204621","https://openalex.org/W2970748231","https://openalex.org/W2982434686","https://openalex.org/W3034999214","https://openalex.org/W3037784242","https://openalex.org/W3105604018","https://openalex.org/W3135427360","https://openalex.org/W3164045210","https://openalex.org/W3174418826","https://openalex.org/W3200130628","https://openalex.org/W4285267582","https://openalex.org/W4287348678","https://openalex.org/W4288265053","https://openalex.org/W4292692470","https://openalex.org/W4293469690","https://openalex.org/W4298422451","https://openalex.org/W4385245566","https://openalex.org/W4385574143"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2982049069","https://openalex.org/W4378498597","https://openalex.org/W3101140821","https://openalex.org/W4287816966","https://openalex.org/W3015650676","https://openalex.org/W4389520445","https://openalex.org/W4387800341","https://openalex.org/W4388347706"],"abstract_inverted_index":{"Learned":[0],"representations":[1,93,114],"at":[2,64],"the":[3,68,84,92,95,100,103],"level":[4,44],"of":[5,45,62,67,91,109],"characters,":[6],"sub-words,":[7],"words,":[8],"and":[9,21,35,111],"sentences,":[10],"have":[11],"each":[12,43],"contributed":[13],"to":[14,39,57,59,78,106,133],"advances":[15],"in":[16,83,126],"understanding":[17],"different":[18,37,60,65],"NLP":[19],"tasks":[20],"linguistic":[22],"phenomena.":[23],"However,":[24],"learning":[25],"textual":[26],"embeddings":[27],"is":[28,130],"costly":[29],"as":[30],"they":[31],"are":[32,115],"tokenization":[33],"specific":[34],"require":[36],"models":[38],"be":[40],"trained":[41],"for":[42],"abstraction.":[46],"We":[47,71,97],"introduce":[48],"a":[49,127],"novel":[50],"language":[51],"representation":[52],"model":[53,104,128],"which":[54,86,129],"can":[55],"learn":[56],"compress":[58],"levels":[61,108],"abstraction":[63,110],"layers":[66,82,101],"same":[69],"model.":[70,96],"apply":[72],"Nonparametric":[73],"Variational":[74],"Information":[75],"Bottleneck":[76],"(NVIB)":[77],"stacked":[79],"Transformer":[80],"self-attention":[81],"encoder,":[85],"encourages":[87],"an":[88],"information-theoretic":[89],"compression":[90,124],"through":[94],"find":[98],"that":[99,112,122],"within":[102],"correspond":[105],"increasing":[107],"their":[113],"more":[116,131],"linguistically":[117],"informed.":[118],"Finally,":[119],"we":[120],"show":[121],"NVIB":[123],"results":[125],"robust":[132],"adversarial":[134],"perturbations.":[135]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}