1 code implementation • 20 Oct 2021 • Shilun Li, Renee Li, Carina Zhang
In this paper, we propose sentiment classification models based on BERT integrated with DRO (Distributionally Robust Classifiers) to improve model performance on datasets with distributional shifts.
1 code implementation • 19 Oct 2021 • Shilun Li, Renee Li, Veronica Peng
In our Paper, we utilized the fine-tuned ALBERT models and implemented combinations of additional layers (e. g. attention layer, RNN layer) on top of them to improve model performance on Stanford Question Answering Dataset (SQuAD 2. 0).
Ranked #86 on Question Answering on SQuAD2.0 (F1 metric)
no code implementations • 28 Nov 2020 • Jussi Karlgren, Renee Li, Eva M Meyersson Milgrom
We use commercially available text analysis technology to process interview text data from a computational social science study.