« Joulin et al. (2016b) » : différence entre les versions
Aller à la navigation
Aller à la recherche
(Page créée avec « * Joulin, Armand, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Hérve Jégou, Tomas Mikolov. 2016. ''Compressing text classification models'', [https://arxiv.org/abs/1612.03651 texte]. '''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 produ... ») |
Aucun résumé des modifications |
||
| Ligne 2 : | Ligne 2 : | ||
'''Abstract''': | '''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." | "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." | ||
[[Category:TAL|Categories]] | [[Category:TAL|Categories]] | ||
Dernière version du 28 octobre 2025 à 16:20
- Joulin, Armand, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Hérve Jégou, Tomas Mikolov. 2016. Compressing text classification models, texte.
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."