Abstract
In this study, we demonstrate the viability of deploying BERT-style models to AWS Lambda in a production environment. Since the freely available pre-trained models are too large to be deployed in this environment, we utilize knowledge distillation and fine-tune the models on proprietary datasets for two real-world tasks: sentiment analysis and semantic textual similarity. As a result, we obtain models that are tuned for a specific domain and deployable in the serverless environment. The subsequent performance analysis shows that this solution does not only report latency levels acceptable for production use but that it is also a cost-effective alternative to small-to-medium size deployments of BERT models, all without any infrastructure overhead.- Anthology ID:
- 2021.naacl-industry.24
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Editors:
- Young-bum Kim, Yunyao Li, Owen Rambow
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 187–195
- Language:
- URL:
- https://aclanthology.org/2021.naacl-industry.24
- DOI:
- 10.18653/v1/2021.naacl-industry.24
- Cite (ACL):
- Marek Suppa, Katarína Benešová, and Andrej Švec. 2021. Cost-effective Deployment of BERT Models in Serverless Environment. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers, pages 187–195, Online. Association for Computational Linguistics.
- Cite (Informal):
- Cost-effective Deployment of BERT Models in Serverless Environment (Suppa et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2021.naacl-industry.24.pdf