NLP Service APIs and Models for Efficient Registration of New Clients

Sahil Shah, Vihari Piratla, Soumen Chakrabarti, Sunita Sarawagi


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.
Anthology ID:
2020.findings-emnlp.357
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:
4007–4012
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.357
DOI:
10.18653/v1/2020.findings-emnlp.357
Bibkey:
Cite (ACL):
Sahil Shah, Vihari Piratla, Soumen Chakrabarti, and Sunita Sarawagi. 2020. NLP Service APIs and Models for Efficient Registration of New Clients. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4007–4012, Online. Association for Computational Linguistics.
Cite (Informal):
NLP Service APIs and Models for Efficient Registration of New Clients (Shah et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.357.pdf
Optional supplementary material:
 2020.findings-emnlp.357.OptionalSupplementaryMaterial.pdf