@librarian-bot\n\t recommend

\n","updatedAt":"2024-07-10T21:13:46.426Z","author":{"_id":"646b8e6f31968a60a0201a12","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/646b8e6f31968a60a0201a12/SU2Gs1NPuk1zoXHwFHl0U.jpeg","fullname":")))?!?(((","name":"stereoplegic","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3926,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7918877601623535},"editors":["stereoplegic"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/646b8e6f31968a60a0201a12/SU2Gs1NPuk1zoXHwFHl0U.jpeg"],"reactions":[],"isReport":false},"replies":[{"id":"668ef99416a6ba9e78da099b","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false},"createdAt":"2024-07-10T21:13:56.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [Optimizing Byte-level Representation for End-to-end ASR](https://huggingface.co/papers/2406.09676) (2024)\n* [T-FREE: Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings](https://huggingface.co/papers/2406.19223) (2024)\n* [Unified Low-rank Compression Framework for Click-through Rate Prediction](https://huggingface.co/papers/2405.18146) (2024)\n* [Retrieval Augmented Zero-Shot Text Classification](https://huggingface.co/papers/2406.15241) (2024)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2024-07-10T21:13:56.130Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7493714094161987},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false,"parentCommentId":"668ef98af65238b10c4f2b0a"}}]}],"primaryEmailConfirmed":false,"paper":{"id":"2106.13302","authors":[{"_id":"65ffa14108d3592936647c34","user":{"_id":"64d1ed038749302d818e7115","avatarUrl":"/avatars/9464c65a170995157f9de753491a5502.svg","isPro":false,"fullname":"Xiang Zhang","user":"fancyzhx","type":"user"},"name":"Xiang Zhang","status":"extracted_pending","statusLastChangedAt":"2024-03-24T03:42:57.907Z","hidden":false},{"_id":"65ffa14108d3592936647c35","user":{"_id":"645408f813dba495b2e016e2","avatarUrl":"/avatars/49df8c12a68df5fd2b36e5f797f4752a.svg","isPro":false,"fullname":"Alexandre Drouin","user":"aldro61","type":"user"},"name":"Alexandre Drouin","status":"extracted_confirmed","statusLastChangedAt":"2024-03-25T01:25:07.894Z","hidden":false},{"_id":"65ffa14108d3592936647c36","user":{"_id":"62d9a30cbfc8699e098791c5","avatarUrl":"/avatars/c80cf773f436748c992d76ca042dd5fb.svg","isPro":false,"fullname":"Raymond Li","user":"RaymondLi","type":"user"},"name":"Raymond Li","status":"extracted_pending","statusLastChangedAt":"2024-03-24T03:42:57.907Z","hidden":false}],"publishedAt":"2021-06-24T20:14:48.000Z","title":"byteSteady: Fast Classification Using Byte-Level n-Gram Embeddings","summary":"This article introduces byteSteady -- a fast model for classification using\nbyte-level n-gram embeddings. byteSteady assumes that each input comes as a\nsequence of bytes. A representation vector is produced using the averaged\nembedding vectors of byte-level n-grams, with a pre-defined set of n. The\nhashing trick is used to reduce the number of embedding vectors. This input\nrepresentation vector is then fed into a linear classifier. A straightforward\napplication of byteSteady is text classification. We also apply byteSteady to\none type of non-language data -- DNA sequences for gene classification. For\nboth problems we achieved competitive classification results against strong\nbaselines, suggesting that byteSteady can be applied to both language and\nnon-language data. Furthermore, we find that simple compression using Huffman\ncoding does not significantly impact the results, which offers an\naccuracy-speed trade-off previously unexplored in machine learning.","upvotes":0,"discussionId":"65ffa14108d3592936647c46","ai_summary":"byteSteady uses byte-level n-gram embeddings and a linear classifier to achieve competitive results in both text and DNA sequence classification, with minimal impact of Huffman coding compression.","ai_keywords":["byte-level n-gram embeddings","hashing trick","linear classifier","gene classification","Huffman coding"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["*"]}">

Papers

arxiv:2106.13302

byteSteady: Fast Classification Using Byte-Level n-Gram Embeddings

Published on Jun 24, 2021

Upvote

Authors:

Xiang Zhang ,

Alexandre Drouin ,

Raymond Li

Abstract

byteSteady uses byte-level n-gram embeddings and a linear classifier to achieve competitive results in both text and DNA sequence classification, with minimal impact of Huffman coding compression.

AI-generated summary

This article introduces byteSteady -- a fast model for classification using byte-level n-gram embeddings. byteSteady assumes that each input comes as a sequence of bytes. A representation vector is produced using the averaged embedding vectors of byte-level n-grams, with a pre-defined set of n. The hashing trick is used to reduce the number of embedding vectors. This input representation vector is then fed into a linear classifier. A straightforward application of byteSteady is text classification. We also apply byteSteady to one type of non-language data -- DNA sequences for gene classification. For both problems we achieved competitive classification results against strong baselines, suggesting that byteSteady can be applied to both language and non-language data. Furthermore, we find that simple compression using Huffman coding does not significantly impact the results, which offers an accuracy-speed trade-off previously unexplored in machine learning.

View arXiv page View PDF Add to collection