NLP Service APIs and Models for Efficient Registration of New Clients

EMNLP(2020)

引用 2|浏览409
暂无评分
摘要
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 large numbers of clients. Neither (hardware deficient) clients nor (heavily subscribed) servers can afford traditional fine tuning. Many clients own little or no labeled data. We initiate a study of adaptation of centralized NLP services to clients, and present one practical and lightweight approach. Each client uses an unsupervised, corpus-based sketch to register to the service. The server uses an auxiliary network to map the sketch to an abstract vector representation, which then informs the main labeling network. When a new client registers with its sketch, it gets immediate accuracy benefits. We demonstrate the success of the proposed architecture using sentiment labeling, NER, and predictive language modeling
更多
查看译文
关键词
efficient registration,new clients,service,models
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要