An Evaluation of Transfer Learning for Classifying Sales Engagement Emails at Large Scale

no code implementations • 19 Apr 2019 • Yong Liu, Pavel Dmitriev, Yifei HUANG, Andrew Brooks, Li Dong

Our results show that fine-tuning of the BERT model outperforms with as few as 300 labeled samples, but underperforms with fewer than 300 labeled samples, relative to all the feature-based approaches using different embeddings.

Language Modelling Transfer Learning