Continuous pretraining and delivery of NLP models to optimize sales engagement

Sales engagement is a complex process that involves many players and touchpoints (such as emails, phone calls, etc.) across different industries and market segments. The rise of sales engagement platforms (SEPs) such as, dramatically improves the productivity of sales reps. Furthermore, machine learning and NLP models in the SEPs bring intelligent assistance into the hands of sales reps.

This presentation gives an overview of the various sales scenarios that benefit from these intelligence capabilities. We illustrate how we leverage public pre-trained language models such as BERT and do further pretraining on different sales engagement domains (market segment etc.) and NLP tasks.

This results in a continuous pretraining and delivery of new NLP models to power scenarios such as automatic email intent classification, named entity extraction from emails, etc., and turning these into reusable knowledge assets. We hope that our experiences with the digital transformation of the sales domain are useful for the broader data science community.

About the speaker

Yong Liu

Principal Data Scientist at

Yong Liu is a Principal Data Scientist at, working on machine learning, NLP, and data science solution to solve problems arising from the sales engagement platform. Previously, he was with Maana Inc. and Microsoft.

Prior to joining Microsoft, he was a Principal Investigator and Senior Research Scientist at the National Center for Supercomputing Applications (NCSA), where he led R&D projects funded by the National Science Foundation and Microsoft Research. Yong holds a Ph.D. from the University of Illinois at Urbana-Champaign.

Presented by