Learn Your Tokens: Word-Pooled Tokenization for Language Modeling. Thawani, A., Ghanekar, S., Zhu, X., & Pujara, J. In Findings of the Association for Computational Linguistics: EMNLP, 2023. bibtex @inproceedings{thawani:emnlpf23,
author = "Thawani, Avijit and Ghanekar, Saurabh and Zhu, Xiaoyuan and Pujara, Jay",
acceptrate = "46.2\%",
arxiv_url = "https://arxiv.org/pdf/2310.11628",
bib_url = "/pubs/bib/thawani-emnlpf23.bib",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP",
doi_url = "https://doi.org/10.18653/v1/2023.findings-emnlp.662",
pdf_url = "/pubs/2023/thawani-emnlpf23/thawani-emnlpf23.pdf",
sec = "conf",
title = "Learn Your Tokens: Word-Pooled Tokenization for Language Modeling",
year = "2023"
}
Downloads: 0
{"_id":"rkaHxLo4sbRuLYDyy","bibbaseid":"thawani-ghanekar-zhu-pujara-learnyourtokenswordpooledtokenizationforlanguagemodeling-2023","author_short":["Thawani, A.","Ghanekar, S.","Zhu, X.","Pujara, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Thawani"],"firstnames":["Avijit"],"suffixes":[]},{"propositions":[],"lastnames":["Ghanekar"],"firstnames":["Saurabh"],"suffixes":[]},{"propositions":[],"lastnames":["Zhu"],"firstnames":["Xiaoyuan"],"suffixes":[]},{"propositions":[],"lastnames":["Pujara"],"firstnames":["Jay"],"suffixes":[]}],"acceptrate":"46.2%","arxiv_url":"https://arxiv.org/pdf/2310.11628","bib_url":"/pubs/bib/thawani-emnlpf23.bib","booktitle":"Findings of the Association for Computational Linguistics: EMNLP","doi_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.662","pdf_url":"/pubs/2023/thawani-emnlpf23/thawani-emnlpf23.pdf","sec":"conf","title":"Learn Your Tokens: Word-Pooled Tokenization for Language Modeling","year":"2023","bibtex":"@inproceedings{thawani:emnlpf23,\n author = \"Thawani, Avijit and Ghanekar, Saurabh and Zhu, Xiaoyuan and Pujara, Jay\",\n acceptrate = \"46.2\\%\",\n arxiv_url = \"https://arxiv.org/pdf/2310.11628\",\n bib_url = \"/pubs/bib/thawani-emnlpf23.bib\",\n booktitle = \"Findings of the Association for Computational Linguistics: EMNLP\",\n doi_url = \"https://doi.org/10.18653/v1/2023.findings-emnlp.662\",\n pdf_url = \"/pubs/2023/thawani-emnlpf23/thawani-emnlpf23.pdf\",\n sec = \"conf\",\n title = \"Learn Your Tokens: Word-Pooled Tokenization for Language Modeling\",\n year = \"2023\"\n}\n\n","author_short":["Thawani, A.","Ghanekar, S.","Zhu, X.","Pujara, J."],"bibbaseid":"thawani-ghanekar-zhu-pujara-learnyourtokenswordpooledtokenizationforlanguagemodeling-2023","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/f/NzF2aGpiFcQTEjHcF/jpujara-2023.bib","dataSources":["8coo8cZMjGAhtHyqT"],"keywords":[],"search_terms":["learn","tokens","word","pooled","tokenization","language","modeling","thawani","ghanekar","zhu","pujara"],"title":"Learn Your Tokens: Word-Pooled Tokenization for Language Modeling","year":2023}