COVID-Q: A Dataset of 1,690 Questions about COVID-19
This dataset consists of COVID-19 questions which have been annotated into a broad category (e.g. Transmission, Prevention) and a more specific class such ...
covid-19 question-answering dataset covid-q bert transformers natural-language-processing attention code paper knn-classification few-shot-learning triplet-loss library research

We present COVID-Q, a set of 1,690 questions about COVID-19 from 13 sources, which we annotate into 15 question categories and 207 question classes. The most common questions in our dataset asked about transmission, prevention, and societal effects of COVID, and we found that many questions that appeared in multiple sources were not answered by any FAQ websites of reputable organizations such as the CDC and FDA. For classifying questions into 15 categories, a BERT baseline scored 58.1% accuracy when trained on 20 examples per class, and for classifying questions into 89 question classes, the baseline achieved 54.6% accuracy. We hope COVID-Q can be helpful either for direct use in developing applied systems or as a domain- specific resource for model evaluation.

Don't forget to tag @JerryWei03 in your comment, otherwise they may not be notified.

Authors original post
Share this project
Similar projects
Zero-shot Neural Retrieval via Domain-targeted Synthetic Queries
Zero-shot learning for ad-hoc retrieval models that relies on synthetic query generation.
Performed exploratory analysis on COVID-19 data made available by John Hopkins University. Wrote a notebook to explain SIR model and based the pandemic on ...
Coronavirus Tracker API
🦠 A simple and fast (< 200ms) API for tracking the global coronavirus (COVID-19, SARS-CoV-2) outbreak. It's written in python using the 🍼 Flask framework.
Potential molecular solutions for COVID-19 using Graph VAEs
Efforts towards proposing a potentially highly active molecule against a target protein of the 2019 Novel Coronavirus.