Keywords: # transformers # transfer learning # zero-shot # classification # NER # QA # human-in-the-loop
We ingest 2 million documents monthly at CB Insights (CBI) to empower tech decision-makers and researchers. As ML/NLP practitioners, we know far too well the holy grail behind this statement: data doesn’t turn into insights by itself; the very first challenge we often face is how to extract relevant information with scale, speed, and precision.
When we started at CBI, NLP was still prehistoric when the “bag of words” walked the earth. Fast forward ten years, the birth of the “attention mechanism” created an NLP explosion and a strong tailwind for teams big and small to ride.
In this talk, we’ll share how we modernized our NLP stack @ CBI Delphi and the challenges we were met with. We’ll discuss lessons learned using transformer models across various tasks and languages, be it fine-tuning for financial NER or zero-shot for customer testimonial extraction. We also want to touch on the open topic of human-AI partnership in two distinct forms. First, specific to data operation, how to achieve both scale and precision with human-in-the-loop. Second, in the era of increasingly powerful super models and ML automation, how our time can be better spent as ML practitioners solving business problems.