Tensorized Embedding Layers
Oleksii Hrinchuk, Valentin Khrulkov, Leyla Mirvakhabova, Elena Orlova, Ivan Oseledets
Abstract
The embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing. However, when the vocabulary is large, the corresponding weight matrices can be enormous, which precludes their deployment in a limited resource setting. We introduce a novel way of parameterizing embedding layers based on the Tensor Train decomposition, which allows compressing the model significantly at the cost of a negligible drop or even a slight gain in performance. We evaluate our method on a wide range of benchmarks in natural language processing and analyze the trade-off between performance and compression ratios for a wide range of architectures, from MLPs to LSTMs and Transformers.- Anthology ID:
- 2020.findings-emnlp.436
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Trevor Cohn, Yulan He, Yang Liu
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4847–4860
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.436
- DOI:
- 10.18653/v1/2020.findings-emnlp.436
- Cite (ACL):
- Oleksii Hrinchuk, Valentin Khrulkov, Leyla Mirvakhabova, Elena Orlova, and Ivan Oseledets. 2020. Tensorized Embedding Layers. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4847–4860, Online. Association for Computational Linguistics.
- Cite (Informal):
- Tensorized Embedding Layers (Hrinchuk et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2020.findings-emnlp.436.pdf
- Data
- IMDb Movie Reviews, SST, WikiText-103