1 code implementation • Findings (ACL) 2022 • Aaron Reich, Jiaao Chen, Aastha Agrawal, Yanzhe Zhang, Diyi Yang
We found that state-of-the-art NER systems trained on CoNLL 2003 training data drop performance dramatically on our challenging set.
no code implementations • 27 Aug 2021 • Harshit Daga, YiWen Chen, Aastha Agrawal, Ada Gavrilovska
For highly distributed environments such as edge computing, collaborative learning approaches eschew the dependence on a global, shared model, in favor of models tailored for each location.