Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its DataCite record; 27 of the 27 references it cites were found in a registry or an index.

FastText.zip: Compressing text classification models

Open access
Joulin, Armand, Grave, Edouard, Bojanowski, Piotr, Douze, Matthijs, Jégou, Hérve, Mikolov, Tomas · 2016 · arXiv

Abstract

We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory. After considering different solutions inspired by the hashing literature, we propose a method built upon product quantization to store word embeddings. While the original technique leads to a loss in accuracy, we adapt this method to circumvent quantization artefacts. Our experiments carried out on several benchmarks show that our approach typically requires two orders of magnitude less memory than fastText while being only slightly inferior with respect to accuracy. As a result, it outperforms the state of the art by a good margin in terms of the compromise between memory usage and accuracy.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

DataCite · 10.48550/arxiv.1612.03651

Cites

27 of 27 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 27 references

Research works printed but not linked: 17

  1. Ashwinkumar Badanidiyuru, Baharan Mirzasoleiman, Amin Karbasi, and Andreas Krause. Streaming submodular maximization: Massive data summarization on the fly. In SIGKDD , pp. 671-680. ACM, 2014.
  2. Mohammad Hossein Bateni, Mohammad Taghi Hajiaghayi, and Morteza Zadimoghaddam. Submodular secretary problem and extensions. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques , pp. 39-52. Springer, 2010.
  3. M. Datar, N. Immorlica, P. Indyk, and V.S. Mirrokni. Locality-sensitive hashing scheme based on pstable distributions. In Proceedings of the Symposium on Computational Geometry , pp. 253-262, 2004.
  4. Misha Denil, Babak Shakibi, Laurent Dinh, Marc-Aurelio Ranzato, and Nando et all de Freitas. Predicting parameters in deep learning. In NIPS , pp. 2148-2156, 2013.
  5. Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun. Optimized product quantization for approximate nearest neighbor search. In CVPR , June 2013.
  6. Yunchao Gong and Svetlana Lazebnik. Iterative quantization: A procrustean approach to learning binary codes. In CVPR , June 2011.
  7. Song Han, Huizi Mao, and William J Dally. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. In ICLR , 2016.
  8. Andrew McCallum and Kamal Nigam. A comparison of event models for naive bayes text classification. In AAAI workshop on learning for text categorization , 1998.
  9. Lukas Meier, Sara Van De Geer, and Peter B¨ uhlmann. The group lasso for logistic regression. Journal of the Royal Statistical Society: Series B (Statistical Methodology) , 70(1):53-71, 2008.
  10. Tomas Mikolov. Statistical language models based on neural networks. In PhD thesis . VUT Brno, 2012.
  11. Tomas Mikolov, Ilya Sutskever, Anoop Deoras, Hai-Son Le, Stefan Kombrink, and J Cernocky. Subword language modeling with neural networks. preprint , 2012.
  12. Behnam Neyshabur and Nathan Srebro. On symmetric and asymmetric lshs for inner product search. In ICML , pp. 1926-1934, 2015.
  13. Jorge S´ anchez and Florent Perronnin. High-dimensional signature compression for large-scale image classification. In CVPR , 2011.
  14. Andreas Stolcke. Entropy-based pruning of backoff language models. arXiv preprint cs/0006025 , 2000. · arXiv
  15. Jingdong Wang, Heng Tao Shen, Jingkuan Song, and Jianqiu Ji. Hashing for similarity search: A survey. arXiv preprint arXiv:1408.2927 , 2014. · arXiv
  16. Sida Wang and Christopher D Manning. Baselines and bigrams: Simple, good sentiment and topic classification. In ACL , 2012.
  17. Xiang Zhang, Junbo Zhao, and Yann LeCun. Character-level convolutional networks for text classification. In NIPS , 2015.

Cited by

See all 1,003

Metadata

Authors
Joulin, A., Grave, E., Bojanowski, P., Douze, M., Jégou, H., & Mikolov, T.
Venue
arXiv
Publisher
arXiv
Published
2016
ISSN
2331-8422 (ISSN-L)
OpenAlex
W2563351168
Cited by
887
References
27
Citations by year
2026: 2 · 2025: 50 · 2024: 104 · 2023: 142 · 2022: 137 · 2021: 164 · 2020: 138 · 2019: 102 · 2018: 37 · 2017: 11
Type
posted content
Language
en
Open access
Locations
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Text and Document Classification Technologies
Keywords
Twitter, online communities, destructive behavior, emoji use, linguistic patterns, COREX, topic extraction, Word Mover's Distance, sentence similarity, data annotation, data augmentation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: FastText.zip: Compressing text classification models. https://app.cochat.ai/papers/10.48550/arxiv.1612.03651
The paper
Joulin, A., Grave, E., Bojanowski, P., Douze, M., Jégou, H., & Mikolov, T. (2016). FastText.zip: Compressing text classification models. arXiv. https://doi.org/10.48550/arxiv.1612.03651

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.