# NutCracker at WNUT-2020 Task 2: Robustly Identifying Informative COVID-19 Tweets using Ensembling and Adversarial Training

Source: [NutCracker at WNUT-2020 Task 2: Robustly Identifying Informative COVID-19 Tweets using Ensembling and Adversarial Training](<https://www.sota2.com/research/paper/68fa68831e209131cea1c922>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:21:17.450Z

Authors: Priyanshu Kumar, Aadarsh Singh

Published: 2020-10-09T02:46:51.000Z

## Abstract

We experiment with COVID-Twitter-BERT and RoBERTa models to identify informative COVID-19 tweets. We further experiment with adversarial training to make our models robust. The ensemble of COVID-Twitter-BERT and RoBERTa obtains a F1-score of 0.9096 (on the positive class) on the test data of WNUT-2020 Task 2 and ranks 1st on the leaderboard. The ensemble of the models trained using adversarial training also produces similar result.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Informative Tweet Identification on WNUT Task 2 2020 (CV)](<https://www.sota2.com/research/sota/informative-tweet-identification-on-wnut-task-2-2020-cv.md>): Informative Tweet Identification; WNUT Task 2 2020 (CV); F1 Score: 96.55.

- [Informative Tweet Identification on WNUT Task 2 2020 (test)](<https://www.sota2.com/research/sota/informative-tweet-identification-on-wnut-task-2-2020-test.md>): Informative Tweet Identification; WNUT Task 2 2020 (test); F1 Score: 90.96.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2010.04335>)

[PDF](<https://arxiv.org/pdf/2010.04335.pdf>)

[Implementation](<https://github.com/kpriyanshu256/WNUT-2020-Task-2>)
