{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:41:19Z","timestamp":1773376879580,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,7]]},"DOI":"10.1109\/isit57864.2024.10619368","type":"proceedings-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T13:25:01Z","timestamp":1724073901000},"page":"2038-2043","source":"Crossref","is-referenced-by-count":1,"title":["TexShape: Information Theoretic Sentence Embedding for Language Models"],"prefix":"10.1109","author":[{"given":"Kaan","family":"Kale","sequence":"first","affiliation":[{"name":"Bo&#x011F;azi&#x00E7;i University,Istanbul,T&#x00FC;rkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Homa","family":"Esfahanizadeh","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs,Murray Hill,NJ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noel","family":"Elias","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Austin,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oguzhan","family":"Baser","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Austin,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muriel","family":"M\u00e9dard","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology (MIT),Cambridge,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sriram","family":"Vishwanath","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Austin,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Devlin","year":"2018","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref2","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref3","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"issue":"240","key":"ref4","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref5","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref6","author":"Zhao","year":"2023","journal-title":"A survey of large language models"},{"key":"ref7","author":"Nalisnick","year":"2018","journal-title":"Do deep generative models know what they dont know?"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139030687"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511841224"},{"key":"ref11","volume-title":"Signals & systems","author":"Oppenheim","year":"1996"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2014.6970882"},{"key":"ref13","first-page":"201","article-title":"The im algorithm: a variational approach to information maximization","volume-title":"Proceedings of the 16th International Conference on Neural Information Processing Systems, ser. NIPS03","author":"Barber","year":"2003"},{"key":"ref14","article-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Chen","year":"2016"},{"key":"ref15","first-page":"7530","article-title":"Improving disentangled text representation learning with information-theoretic guidance","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Cheng"},{"key":"ref16","article-title":"MINE: mutual information neural estimation","author":"Belghazi","year":"2018","journal-title":"CoRR, vol. abs\/1801.04062"},{"key":"ref17","volume-title":"Regularized mutual information neural estimation","author":"Choi","year":"2021"},{"key":"ref18","article-title":"Understanding the limitations of variational mutual information estimators","volume-title":"International Conference on Learning Representations","author":"Song","year":"2020"},{"key":"ref19","author":"Kim","year":"2023","journal-title":"Crypto-mine: Cryptanalysis via mutual information neural estimation"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49357.2023.10095632","article-title":"InfoShape: Task-based neural data shaping via mutual information","volume-title":"ICASSP 2023 \u2013 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Esfahanizadeh"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160280102"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.066138"},{"key":"ref23","article-title":"Online algorithms and stochastic approximations","volume-title":"Online Learning and Neural Networks","author":"Bottou","year":"1998"},{"key":"ref24","author":"Beutel","year":"2017","journal-title":"Data decisions and theoretical implications when adversarially learning fair representations"},{"key":"ref25","first-page":"16857","article-title":"Mpnet: Masked and permuted pre-training for language understanding","volume":"33","author":"Song","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref27","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","author":"Socher"},{"key":"ref28","article-title":"Coronavirus tweets nlp - text classification","volume-title":"Kaggle.com","author":"Miglani","year":"2021"},{"key":"ref29","first-page":"1112","article-title":"A broad-coverage challenge corpus for sentence understanding through inference","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","author":"Williams","year":"2018"},{"key":"ref30","volume-title":"Compressed models for co-reference resolution: enhancing efficiency with debiased word embeddings","author":"Ioannides","year":"2023"}],"event":{"name":"2024 IEEE International Symposium on Information Theory (ISIT)","location":"Athens, Greece","start":{"date-parts":[[2024,7,7]]},"end":{"date-parts":[[2024,7,12]]}},"container-title":["2024 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10619013\/10619074\/10619368.pdf?arnumber=10619368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:28:57Z","timestamp":1773347337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10619368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,7]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/isit57864.2024.10619368","relation":{},"subject":[],"published":{"date-parts":[[2024,7,7]]}}}