{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,28]],"date-time":"2025-12-28T15:16:04Z","timestamp":1766934964609,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3592063","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"2389-2393","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["SimTDE: Simple Transformer Distillation for Sentence Embeddings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3447-2642","authenticated-orcid":false,"given":"Jian","family":"Xie","sequence":"first","affiliation":[{"name":"University of Central Florida, Orlando, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9182-6733","authenticated-orcid":false,"given":"Xin","family":"He","sequence":"additional","affiliation":[{"name":"Amazon Alexa, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5079-4299","authenticated-orcid":false,"given":"Jiyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon Alexa, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2258-0304","authenticated-orcid":false,"given":"Zimeng","family":"Qiu","sequence":"additional","affiliation":[{"name":"Amazon Alexa, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6153-0483","authenticated-orcid":false,"given":"Ali","family":"Kebarighotbi","sequence":"additional","affiliation":[{"name":"Amazon Alexa, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2825-1979","authenticated-orcid":false,"given":"Farhad","family":"Ghassemi","sequence":"additional","affiliation":[{"name":"Amazon Alexa, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Samuel R Bowman Gabor Angeli Christopher Potts and Christopher D Manning. 2015. The SNLI corpus. (2015)."},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of the 2017 SEMVAL International Workshop on Semantic Evaluation (2017","author":"Cer Daniel","year":"2017","unstructured":"Daniel Cer, Mona Diab, Eneko Agirre, Inigo Lopez-Gazpio, and Lucia Specia. 2017. Semantic textual similarity-multilingual and cross-lingual focused evaluation. In Proceedings of the 2017 SEMVAL International Workshop on Semantic Evaluation (2017). https:\/\/doi. org\/10.18653\/v1\/s17--2001."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2029"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1070"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367564"},{"key":"e_1_3_2_2_8_1","volume-title":"Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115","author":"Gong Yunchao","year":"2014","unstructured":"Yunchao Gong, Liu Liu, Ming Yang, and Lubomir Bourdev. 2014. Compressing deep convolutional networks using vector quantization. arXiv preprint arXiv:1412.6115 (2014)."},{"key":"e_1_3_2_2_9_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J Dally. 2015a. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_3_2_2_10_1","volume-title":"Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William J. Dally. 2015b. Learning both Weights and Connections for Efficient Neural Network. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7--12, 2015, Montreal, Quebec, Canada, Corinna Cortes, Neil D. Lawrence, Daniel D. Lee, Masashi Sugiyama, and Roman Garnett (Eds.). 1135--1143. https:\/\/proceedings.neurips.cc\/paper\/2015\/hash\/ae0eb3eed39d2bcef4622b2499a05fe6-Abstract.html"},{"key":"e_1_3_2_2_11_1","unstructured":"Geoffrey Hinton Oriol Vinyals Jeff Dean et al. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 Vol. 2 7 (2015)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_13_1","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Liu Fangyu","year":"2022","unstructured":"Fangyu Liu, Yunlong Jiao, Jordan Massiah, Emine Yilmaz, and Serhii Havrylov. 2022. Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=AmUhwTOHgm"},{"key":"e_1_3_2_2_14_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC 2014","author":"Marelli Marco","year":"2014","unstructured":"Marco Marelli, Stefano Menini, Marco Baroni, Luisa Bentivogli, Raffaella Bernardi, and Roberto Zamparelli. 2014. A SICK cure for the evaluation of compositional distributional semantic models. In Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC 2014, Reykjavik, Iceland, May 26--31, 2014, Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asunci\u00f3 n Moreno, Jan Odijk, and Stelios Piperidis (Eds.). European Language Resources Association (ELRA), 216--223. http:\/\/www.lrec-conf.org\/proceedings\/lrec2014\/summaries\/363.html"},{"key":"e_1_3_2_2_16_1","volume-title":"Interspeech","author":"McGowan Ross","year":"2021","unstructured":"Ross McGowan, Jinru Su, Vince DiCocco, Thejaswi Muniyappa, and Grant Strimel. 2021. SmallER: Scaling neural entity resolution for edge devices. In Interspeech 2021. https:\/\/www.amazon.science\/publications\/smaller-scaling-neural-entity-resolution-for-edge-devices"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_2_18_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2015","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015. FitNets: Hints for Thin Deep Nets. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6550"},{"key":"e_1_3_2_2_19_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_2_20_1","volume-title":"Whitening sentence representations for better semantics and faster retrieval. arXiv preprint arXiv:2103.15316","author":"Su Jianlin","year":"2021","unstructured":"Jianlin Su, Jiarun Cao, Weijie Liu, and Yangyiwen Ou. 2021. Whitening sentence representations for better semantics and faster retrieval. arXiv preprint arXiv:2103.15316 (2021)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"e_1_3_2_2_22_1","volume-title":"Multilingual Neural Machine Translation with Knowledge Distillation. In 7th International Conference on Learning Representations, ICLR 2019","author":"Tan Xu","year":"2019","unstructured":"Xu Tan, Yi Ren, Di He, Tao Qin, Zhou Zhao, and Tie-Yan Liu. 2019. Multilingual Neural Machine Translation with Knowledge Distillation. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6--9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=S1gUsoR9YX"},{"key":"e_1_3_2_2_23_1","volume-title":"Distilling task-specific knowledge from bert into simple neural networks. arXiv preprint arXiv:1903.12136","author":"Tang Raphael","year":"2019","unstructured":"Raphael Tang, Yao Lu, Linqing Liu, Lili Mou, Olga Vechtomova, and Jimmy Lin. 2019. Distilling task-specific knowledge from bert into simple neural networks. arXiv preprint arXiv:1903.12136 (2019)."},{"key":"e_1_3_2_2_24_1","volume-title":"Well-read students learn better: The impact of student initialization on knowledge distillation. arXiv preprint arXiv:1908.08962","author":"Turc Iulia","year":"2019","unstructured":"Iulia Turc, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Well-read students learn better: The impact of student initialization on knowledge distillation. arXiv preprint arXiv:1908.08962, Vol. 13 (2019)."},{"key":"e_1_3_2_2_25_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4--9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998--6008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_2_26_1","volume-title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers. ArXiv","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers. ArXiv, Vol. abs\/2002.10957 (2020)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.393"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Taipei Taiwan","acronym":"SIGIR '23"},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3592063","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3592063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:38:03Z","timestamp":1750178283000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3592063"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":28,"alternative-id":["10.1145\/3539618.3592063","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3592063","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}