Shah, Sahil ; Piratla, Vihari ; Chakrabarti, Soumen ; Sarawagi, Sunita (2020) NLP Service APIs and Models for Efficient Registration of New Clients In: Findings of the Association for Computational Linguistics: EMNLP 2020.
![]() |
PDF
528kB |
Official URL: http://doi.org/10.18653/v1/2020.findings-emnlp.357
Related URL: http://dx.doi.org/10.18653/v1/2020.findings-emnlp.357
Abstract
State-of-the-art NLP inference uses enormous neural architectures and models trained for GPU-months, well beyond the reach of most consumers of NLP. This has led to one-size-fits-all public API-based NLP service models by major AI companies, serving millions of clients. They cannot afford traditional fine tuning for individual clients. Many clients cannot even afford significant fine tuning, and own little or no labeled data. Recognizing that word usage and salience diversity across clients leads to reduced accuracy, we initiate a study of practical and lightweight adaptation of centralized NLP services to clients. Each client uses an unsupervised, corpus-based sketch to register to the service. The server modifies its network mildly to accommodate client sketches, and occasionally trains the augmented network over existing clients. When a new client registers with its sketch, it gets immediate accuracy benefits. We demonstrate the proposed architecture using sentiment labeling, NER, and predictive language modeling.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Source: | Copyright of this article belongs to Association for Computational Linguistics |
ID Code: | 130886 |
Deposited On: | 01 Dec 2022 06:01 |
Last Modified: | 27 Jan 2023 09:32 |
Repository Staff Only: item control page