HackerPapers

arXiv:1607.01759cs.CL

Bag of Tricks for Efficient Text Classification

Armand Joulin, Edouard Grave, Piotr Bojanowski, Tomas Mikolov

Abstract

This paper explores a simple and efficient baseline for text classification. Our experiments show that our fast text classifier fastText is often on par with deep learning classifiers in terms of accuracy, and many orders of magnitude faster for training and evaluation. We can train fastText on more than one billion words in less than ten minutes using a standard multicore~CPU, and classify half a million sentences among~312K classes in less than a minute.

arXiv comments
Journal reference
DOI
Subjects
cs.CLComputation and Language

On Hacker News

Linked by 6 identifiable commenters in 6 comments across 4 threads, from Aug 2016 to Jun 2024. Found in 2 HN submissions from Jul 2016 to Jul 2016. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments4 threads

  1. Ask HN: How to pivot to a Machine Learning engineer? 1 comment

    • A lot of great takes in this thread, but let me give more perspective being a MLE/MLOps Engineer myself around the math. For me mathematics and statistics represent (a) unemployment insurance since it give me a lot of transitivity around roles in the space,(b) give me a good…

      brazaView on HNParent context

  2. Understanding word vectors 1 comment

    • The cognoscenti already know this, but word vectors are a game changer in the multi-class text classification game. Finding the correct representation of text makes the classification task so much easier. For my problem (1000+ total classes, 1 class per input), I experimented…

      wencView on HNParent context

  3. Bag of Tricks for Efficient Text Classification 1 comment

    • That FB hand-off page has an annoying auto refresh with NoScript enabled. So, here's the PDF it points to. I guess I'll change it from linking the PDF document to a link to its abstract page, while I'm at it. http://arxiv.org/abs/1607.01759v3

      pasbesoinView on HNParent context

  4. FastText – Library for fast text representation and classification 3 comments

    • Link to the paper: https://arxiv.org/abs/1607.01759 Quotes from the paper: Both char-CNN and VDCNN are trained on a NVIDIA Tesla K40 GPU, while our models are trained on a CPU using 20 threads. Table2 shows that methods using convolutions are several orders of magnitude slower…

      smhxView on HNParent context

    • Just to mirror what was said on the thread a month ago when the paper came out[1], if you're interested in FastText I'd strongly recommend checking out Vowpal Wabbit[2] and BIDMach[3]. My main issue is that the FastText paper [7] only compares to other intensive deep methods and…

      SmerityView on HNParent context

    • Links to the relevant papers: Bag of Tricks for Efficient Text Classification: https://arxiv.org/abs/1607.01759v2 Enriching Word Vectors with Subword Information: https://arxiv.org/abs/1607.04606 Both fantastic papers. For those who aren't aware, Mikolov also helped create…

      koughView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.