Summary
In this chapter, we have examined an approach to NLP competitions, specifically Google Quest Q&A Labeling. We began with a baseline utilizing vintage methods (summary/descriptive characteristics of the text fields), combined with embeddings from a pretrained model. This gave us a foundational understanding of the challenges involved, and we then moved on to a discussion of more advanced solutions that performed well in the competition. This chapter should give you an understanding of how to approach NLP classification contests; those new to the field will benefit from the baseline solution, while more experienced Kagglers can benefit from the guidance that the published medal approaches provide.
Join our book’s Discord space
Join our Discord community to meet like-minded people and learn alongside more than 2000 members at:
https://packt.link/KaggleDiscord
