# FastText.zip: Compressing text classification models

Source: [FastText.zip: Compressing text classification models](<https://www.sota2.com/research/paper/68fa63041e209131ce9fc5c4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:31:19.733Z

Authors: Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, H\\'erve J\\'egou, Tomas Mikolov

Published: 2016-12-12T12:51:03.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [MEP-Lobby link discovery on Retweets](<https://www.sota2.com/research/sota/mep-lobby-link-discovery-on-retweets.md>): MEP-Lobby link discovery; Retweets; AUC: 0.687.

- [MEP-Lobby link discovery on Meetings](<https://www.sota2.com/research/sota/mep-lobby-link-discovery-on-meetings.md>): MEP-Lobby link discovery; Meetings; AUC: 65.2.

- [Sentiment Analysis on IMDB (test)](<https://www.sota2.com/research/sota/sentiment-analysis-on-imdb-test.md>): Sentiment Analysis; IMDB (test); Accuracy: 87.11.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1612.03651>)

[PDF](<https://arxiv.org/pdf/1612.03651.pdf>)
