Dense Feature Memory Augmented Transformers for COVID-19 Vaccination Search Classification

TL;DR

This paper introduces a novel Transformer-based model with dense feature memory tokens for classifying COVID-19 vaccination-related search queries, significantly improving search insight accuracy.

Contribution

It proposes a new method of integrating dense features as memory tokens in Transformers, enhancing COVID-19 vaccination query classification performance.

Findings

15% improvement in F1 score

14% increase in precision

Effective integration of dense features as memory tokens

Abstract

With the devastating outbreak of COVID-19, vaccines are one of the crucial lines of defense against mass infection in this global pandemic. Given the protection they provide, vaccines are becoming mandatory in certain social and professional settings. This paper presents a classification model for detecting COVID-19 vaccination related search queries, a machine learning model that is used to generate search insights for COVID-19 vaccinations. The proposed method combines and leverages advancements from modern state-of-the-art (SOTA) natural language understanding (NLU) techniques such as pretrained Transformers with traditional dense features. We propose a novel approach of considering dense features as memory tokens that the model can attend to. We show that this new modeling approach enables a significant improvement to the Vaccine Search Insights (VSI) task, improving a strong well-established gradient-boosting baseline by relative +15% improvement in F1 score and +14% in precision.